Mingyu Ding

EDBT 2026 Demo / reviewers in the wild / expert

dblp:188/5243 · DBLP profile ↗

← Back

69ranked-venue papers

12as first author

56since 2021 · last 2026

0000-0001-6556-8359ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 67 · 12 first-author · 54 since 2021Graphics, computer vision, multimedia, augmented reality and games · 25 · 9 first-author · 17 since 2021Systems, architecture and hardware · 10 · 9 since 2021Applied, interdisciplinary, general and emerging computing · 1 · 1 since 2021

Year	Publication	Venue	Position
2026	Unlocking the Power of Large Multimodal Models for Robot Learning: Robustness, Generalization, and Opportunities abstract Large multimodal models (LMMs) have revolutionized AI by demonstrating remarkable capabilities in vision, language, audio, and other domains, particularly in understanding and generalization tasks. Yet, moving beyond passive understanding to active interaction requires embodied agents, such as robots, that can harness the capabilities of AI models to act within the physical world. My core research aims to build embodied agents that reason about and interact with the physical world with human-like commonsense. Specifically, I design algorithms and representations that enable robots to perceive their environment, reason about physical properties, and plan long-horizon actions for both manipulation and locomotion. These advances are grounded in the integration of large-scale AI models with embodied control. I organize this agenda into three stages: (1) injecting actions into LMMs to form vision–language–action (VLA) models; (2) learning from human motion and contact to enrich physical reasoning; and (3) advancing whole-body robot loco-manipulation guided by LMMs toward embodied artificial general intelligence (AGI). The talk details recent advances in leveraging LMMs for robot learning, emphasizing the promise of robust generalization across diverse environments, tasks, and modalities. I will highlight contributions at the intersection of perception, reasoning, and control, and outline open challenges and future opportunities toward enabling humanoid robots that can robustly understand, interact, and collaborate with humans in complex real-world settings. Mingyu Ding	AAAI	1
2026	ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction abstract Large language models (LLMs) are increasingly used in scientific domains. While they can produce reasoning-like content via methods such as chain-of-thought prompting, these outputs are typically unstructured and informal, obscuring whether models truly understand the fundamental reasoning paradigms that underpin scientific inference. To address this, we introduce a novel task named Latent Reasoning Chain Extraction (ARCHE), in which models must decompose complex reasoning arguments into combinations of standard reasoning paradigms in the form of a Reasoning Logic Tree (RLT). In an RLT, all reasoning steps are explicitly categorized as one of three variants of Peirce’s fundamental inference modes: deduction, induction, or abduction. To facilitate this task, we release ARCHE Bench, a new benchmark derived from 70 Nature Communications articles, including more than 1,900 references and 38,000 viewpoints. We propose two logic-aware evaluation metrics: Entity Coverage (EC) for content completeness and Reasoning Edge Accuracy (REA) for step-by-step logical validity. Evaluations on 10 leading LLMs on ARCHE Bench reveal that models exhibit a trade-off between REA and EC, and none are yet able to extract a complete and standard reasoning chain. These findings highlight a substantial gap between the abilities of current reasoning models and the rigor required for scientific argumentation. Pengze Li, Junchi Yu, Mingyu Ding, Wanli Ouyang, Shixiang Tang, Xi Chen 0004	AAAI	5
2026	EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning abstract Abstract The pursuit of artificial general intelligence (AGI) has been accelerated by Multimodal Large Language Models (MLLMs), which exhibit superior reasoning, generalization capabilities, and proficiency in processing multimodal inputs. A crucial milestone in the evolution of AGI is the attainment of human-level planning, a fundamental ability for making informed decisions in complex environments, and solving a wide range of real-world problems. Despite the impressive advancements in MLLMs, a question remains: How far are current MLLMs from achieving human-level planning? To shed light on this question, we introduce EgoPlan-Bench, a comprehensive benchmark to evaluate the planning abilities of MLLMs in real-world scenarios from an egocentric perspective, mirroring human perception. EgoPlan-Bench emphasizes the evaluation of planning capabilities of MLLMs, featuring realistic tasks, diverse action plans, and intricate visual observations. Our rigorous evaluation of a wide range of MLLMs reveals that EgoPlan-Bench poses significant challenges, highlighting a substantial scope for improvement in MLLMs to achieve human-level task planning. To facilitate this advancement, we further present EgoPlan-IT, a specialized instruction-tuning dataset that effectively enhances model performance on EgoPlan-Bench. We have made all the codes, data, and a maintained benchmark leaderboard available at https://chenyi99.github.io/ego_plan/ to advance future research. Yi Chen 0019, Yuying Ge, Yixiao Ge, Mingyu Ding, Bohao Li 0002, Rui Wang 0092, Ruifeng Xu 0001, Ying Shan, Xihui Liu	Int. J. Comput. Vis.	4
2026	Toward Unified Expertise: Learning a Single Vision Model From Diverse Perception abstract Multi-task learning (MTL) presents greater optimization challenges than single-task learning (STL) due to conflicting gradients across tasks. While parameter sharing promotes cooperation among related tasks, many tasks require specialized representations. To balance cooperation and specialization, we propose Mod-Squad (Chen et al. 2023), a modular transformer-based model composed of a "squad" of experts. Each task activates a sparse subset of experts through a differentiable matching process, guided by a novel mutual information-based loss. This modular structure avoids full backbone sharing and scales effectively with the number of tasks and dataset size. In this extended version, we generalize Mod-Squad to support multi-dataset pre-training, enabling joint learning across disjoint, single-task datasets (e.g., ImageNet, COCO, ADE20 K). This is achieved via a new formulation of the mutual information loss that unifies learning across heterogeneous sources. More importantly, while most prior work in large models has focused on efficiency, few have explored adjustable efficiency. In this study, we further evaluate the model's generalization to downstream tasks and introduce a set of efficient adaptation techniques that leverage Mod-Squad's modularity for flexible fine-tuning-enabling dynamic adjustment of model size, parameter count, and computational cost. Additionally, we present a hybrid adaptation scheme that combines these techniques to achieve favorable performance-efficiency trade-offs. In summary, Mod-Squad provides a robust foundation for sparse modular models that can learn from diverse supervision and datasets. Its emergent modularity enables strong generalization, decomposition into high-performing components, and rapid, resource-efficient adaptation for downstream applications. Zitian Chen, Mingyu Ding, Yikang Shen, Erik G. Learned-Miller, Chuang Gan 0001	IEEE Trans. Pattern Anal. Mach. Intell.	2
2025	CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians abstract Recent breakthroughs in text-guided image generation have significantly advanced the field of 3D generation. While generating a single high-quality 3D object is now feasible, generating multiple objects with reasonable interactions within a 3D space, a.k.a. compositional 3D generation, presents substantial challenges. This paper introduces COMPGS, a novel generative framework that employs 3D Gaussian Splatting (GS) for efficient, compositional text-to-3D content generation. To achieve this goal, two core designs are proposed: (1) 3D Gaussians Initialization with 2D compositionality: We transfer the well-established 2D compositionality to initialize the Gaussian parameters on an entity-by-entity basis, ensuring both consistent 3D priors for each entity and reasonable interactions among multiple entities; (2) Dynamic Optimization: We propose a dynamic strategy to optimize 3D Gaussians using Score Distillation Sampling (SDS) loss. COMPGS first automatically decomposes 3D Gaussians into distinct entity parts, enabling optimization at both the entity and composition levels. Additionally, COMPGS optimizes across objects of varying scales by dynamically adjusting the spatial parameters of each entity, enhancing the generation of fine-grained details, particularly in smaller entities. Qualitative comparisons and quantitative evaluations on T3Bench demonstrate the effectiveness of COMPGS in generating compositional 3D objects with superior image quality and semantic alignment over existing methods. COMPGS can also be easily extended to progressively adding 3D objects, facilitating complex scene generation. We hope COMPGS will provide new insights to the compositional 3D generation. Chongjian Ge, Chenfeng Xu, Yuanfeng Ji, Chensheng Peng, Masayoshi Tomizuka, Ping Luo 0002, Mingyu Ding, Varun Jampani	CVPR	7
2025	DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation abstract Dexterous manipulation with contact-rich interactions is crucial for advanced robotics. While recent diffusion-based planning approaches show promise for simple manipulation tasks, they often produce unrealistic ghost states (e.g., the object automatically moves without hand contact) or lack adaptability when handling complex sequential interactions. In this work, we introduce DexHand-Diff, an interaction-aware diffusion planning framework for adaptive dexterous manipulation. DexHandDiff models joint state-action dynamics through a dual-phase diffusion process which consists of pre-interaction contact alignment and post-contact goal-directed control, enabling goal-adaptive generalizable dexterous manipulation. Additionally, we incorporate dynamics model-based dual guidance and leverage large language models for automated guidance function generation, enhancing generalizability for physical interactions and facilitating diverse goal adaptation through language cues. Experiments on physical interaction tasks such as door opening, pen and block reorientation, object relocation, and hammer striking demonstrate DexHandDiff’s effectiveness on goals outside training distributions, achieving over twice the average success rate (59.2% vs. 29.5%) compared to existing methods. Our framework achieves an average of 70.7% success rate on goal adaptive dexterous tasks, highlighting its robustness and flexibility in contact-rich manipulation. Zhixuan Liang, Yao Mu 0001, Tianxing Chen, Wenqi Shao, Masayoshi Tomizuka, Ping Luo 0002, Mingyu Ding	CVPR	9
2025	RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins abstract In the rapidly advancing field of robotics, dual-arm co-ordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demonstration data and real-world-aligned evaluation benchmarks severely limits such development. To address this, we introduce RoboTwin, a generative digital twin framework that uses 3D generative foundation models and large language models to produce diverse expert datasets and provide a real-world-aligned evaluation platform for dual-arm robotic tasks. Specifically, RoboTwin creates varied digital twins of objects from single 2D images, generating realistic and interactive scenarios. It also introduces a spatial relation-aware code generation framework that combines object annotations with large language models to break down tasks, determine spatial constraints, and generate precise robotic movement code. Our framework offers a comprehensive benchmark with both simulated and real-world data, enabling standardized evaluation and better alignment between simulated training and real-world performance. We validated our approach using the open-source COBOT Magic Robot platform. Policies pre-trained on RoboTwin-generated data and fine-tuned with limited real-world samples demonstrate significant potential for enhancing dual-arm robotic manipulation systems by improving success rates by over 70% for single-arm tasks and over 40% for dual-arm tasks compared to models trained solely on real-world data. Yao Mu 0001, Tianxing Chen, Zanxin Chen, Shijia Peng, Zhiqian Lan, Zhixuan Liang, Qiaojun Yu, Yude Zou, Mingkun Xu, Lunkai Lin, Mingyu Ding, Ping Luo 0002	CVPR	13
2025	Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos Yi Chen 0019, Yuying Ge, Weiliang Tang, Yizhuo Li 0001, Yixiao Ge, Mingyu Ding, Ying Shan, Xihui Liu	ICCV	6
2025	X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios abstract Recent advancements have exploited diffusion models for the synthesis of either LiDAR point clouds or camera image data in driving scenarios. Despite their success in modeling single-modality data marginal distribution, there is an under- exploration in the mutual reliance between different modalities to describe com- plex driving scenes. To fill in this gap, we propose a novel framework, X-DRIVE, to model the joint distribution of point clouds and multi-view images via a dual- branch latent diffusion model architecture. Considering the distinct geometrical spaces of the two modalities, X-DRIVE conditions the synthesis of each modality on the corresponding local regions from the other modality, ensuring better alignment and realism. To further handle the spatial ambiguity during denoising, we design the cross-modality condition module based on epipolar lines to adaptively learn the cross-modality local correspondence. Besides, X-DRIVE allows for controllable generation through multi-level input conditions, including text, bounding box, image, and point clouds. Extensive results demonstrate the high-fidelity synthetic results of X-DRIVE for both point clouds and multi-view images, adhering to input conditions while ensuring reliable cross-modality consistency. Our code will be made publicly available at https://github.com/yichen928/X-Drive. Yichen Xie 0002, Chenfeng Xu, Chensheng Peng, Shuqi Zhao, Nhat Ho, Alexander T. Pham, Mingyu Ding, Masayoshi Tomizuka	ICLR	7
2025	MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models abstract Interleaved multimodal comprehension and generation, enabling models to produce and interpret both images and text in arbitrary sequences, have become a pivotal area in multimodal learning. Despite significant advancements, the evaluation of this capability remains insufficient. Existing benchmarks suffer from limitations in data scale, scope, and evaluation depth, while current evaluation metrics are often costly or biased, lacking in reliability for practical applications. To address these challenges, we introduce MMIE, a large-scale knowledge-intensive benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models (LVLMs). MMIE comprises 20K meticulously curated multimodal queries, spanning 3 categories, 12 fields, and 102 subfields, including mathematics, coding, physics, literature, health, and arts. It supports both interleaved inputs and outputs, offering a mix of multiple-choice and open-ended question formats to evaluate diverse competencies. Moreover, we propose a reliable automated evaluation metric, leveraging a scoring model fine-tuned with human-annotated data and systematic evaluation criteria, aimed at reducing bias and improving evaluation accuracy. Extensive experiments demonstrate the effectiveness of our benchmark and metrics in providing a comprehensive evaluation of interleaved LVLMs. Specifically, we evaluate eight LVLMs, revealing that even the best models show significant room for improvement, with most achieving only moderate results. We believe MMIE will drive further advancements in the development of interleaved LVLMs. Peng Xia 0005, Siwei Han, Shi Qiu 0016, Yiyang Zhou, Zhaoyang Wang 0004, Zhaorun Chen, Chenhang Cui, Mingyu Ding, Huaxiu Yao	ICLR	9
2025	WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving abstract Language models uncover unprecedented abilities in analyzing driving scenarios, owing to their limitless knowledge accumulated from text-based pre-training. Naturally, they should particularly excel in analyzing rule-based interactions, such as those triggered by traffic laws, which are well documented in texts. However, such interaction analysis remains underexplored due to the lack of dedicated language datasets that address it. Therefore, we propose Waymo Open Motion Dataset-Reasoning (WOMD-Reasoning), a comprehensive large-scale Q&As dataset built on WOMD focusing on describing and reasoning traffic rule-induced interactions in driving scenarios. WOMD-Reasoning also presents by far the largest multi-modal Q&A dataset, with 3 million Q&As on real-world driving scenarios, covering a wide range of driving topics from map descriptions and motion status descriptions to narratives and analyses of agents' interactions, behaviors, and intentions. To showcase the applications of WOMD-Reasoning, we design Motion-LLaVA, a motion-language model fine-tuned on WOMD-Reasoning. Quantitative and qualitative evaluations are performed on WOMD-Reasoning dataset as well as the outputs of Motion-LLaVA, supporting the data quality and wide applications of WOMD-Reasoning, in interaction predictions, traffic rule compliance plannings, etc. The dataset and its vision modal extension are available on https://waymo.com/open/download/. The codes & prompts to build it are available on https://github.com/yhli123/WOMD-Reasoning. Cunxin Fan, Chongjian Ge, Seth Z. Zhao, Chenran Li, Chenfeng Xu, Huaxiu Yao, Masayoshi Tomizuka, Bolei Zhou, Chen Tang 0001, Mingyu Ding	ICML	11
2025	TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection abstract Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a teacher-student framework in which machine-generated pseudo-labels on a large unlabeled dataset are used in combination with a small manually-labeled dataset for training. In this work, we address the problem of improving pseudo-label quality through leveraging long- term temporal information captured in driving scenes. More specifically, we leverage pre-trained motion-forecasting models to generate object trajectories on pseudo-labeled data to further enhance the student model training. Our approach improves pseudo-label quality in two distinct manners: first, we suppress false positive pseudo-labels through establishing consistency across multiple frames of motion forecasting outputs. Second, we compensate for false negative detections by directly inserting predicted object tracks into the pseudo-labeled scene. Experiments on the nuScenes dataset demonstrate the effectiveness of our approach, improving the performance of standard semi-supervised approaches in a variety of settings. Philip L. Jacobson, Yichen Xie 0002, Mingyu Ding, Chenfeng Xu, Masayoshi Tomizuka, Ming C. Wu	ICRA	3
2025	Embodiment-agnostic Action Planning via Object-Part Scene Flow abstract Observing that the key for robotic action planning is to understand the target-object motion when its associated part is manipulated by the end effector, we propose to generate the 3D object-part scene flow and extract its transformations to solve the action trajectories for diverse embodiments. The advantage of our approach is that it derives the robot action explicitly from object motion prediction, yielding a more robust policy by understanding the object motions. Also, beyond policies trained on embodiment-centric data, our method is embodiment-agnostic, generalizable across diverse embodiments, and being able to learn from human demonstrations. Our method comprises three components: an object-part predictor to locate the part for the end effector to manipulate, an RGBD video generator to predict future RGBD videos, and a trajectory planner to extract embodiment-agnostic transformation sequences and solve the trajectory for diverse embodiments. Trained on videos even without trajectory data, our method still outperforms existing works significantly by 27.7% and 26.2% on the prevailing virtual environments MetaWorld and Franka-Kitchen, respectively. Furthermore, we conducted real-world experiments, showing that our policy, trained only with human demonstration, can be deployed to various embodiments. Weiliang Tang, Jia-Hui Pan, Jianshu Zhou, Huaxiu Yao, Yun-Hui Liu 0001, Masayoshi Tomizuka, Mingyu Ding, Chi-Wing Fu	ICRA	8
2025	Physics-Aware Robotic Palletization With Online Masking Inference abstract The efficient planning of stacking boxes, especially in the online setting where the sequence of item arrivals is unpredictable, remains a critical challenge in modern warehouse and logistics management. Existing solutions often address box size variations, but overlook their intrinsic and physical properties, such as density and rigidity, which are crucial for real-world applications. We use reinforcement learning (RL) to solve this problem by employing action space masking to direct the RL policy toward valid actions. Unlike previous methods that rely on heuristic stability assessments which are difficult to assess in physical scenarios, our framework utilizes online learning to dynamically train the action space mask, eliminating the need for manual heuristic design. Extensive experiments demonstrate that our proposed method outperforms existing state-of-the-arts. Furthermore, we deploy our learned task planner in a real-world robotic palletizer, validating its practical applicability in operational settings. The code is available at https://github.com/tianqi-zh/palletization. Zheng Wu 0002, Boyuan Liang, Scott Moura, Masayoshi Tomizuka, Mingyu Ding	ICRA	8
2025	ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis abstract Vision-language-action (VLA) models present a promising paradigm by training policies directly on real robot datasets like Open X-Embodiment. However, the high cost of real-world data collection hinders further data scaling, thereby restricting the generalizability of VLAs. In this paper, we introduce ReBot, a novel real-to-sim-to-real approach for scaling real robot datasets and adapting VLA models to target domains, which is the last-mile deployment challenge in robot manipulation. Specifically, ReBot replays real-world robot trajectories in simulation to diversify manipulated objects (real-to-sim), and integrates the simulated movements with inpainted real-world background to synthesize physically realistic and temporally consistent robot videos (sim-to-real). Our approach has several advantages: 1) it enjoys the benefit of real data to minimize the sim-to-real gap; 2) it leverages the scalability of simulation; and 3) it can generalize a pretrained VLA to a target domain with fully automated data pipelines. Extensive experiments in both simulation and real-world environments show that ReBot significantly enhances the performance and robustness of VLAs. For example, in SimplerEnv with the WidowX robot, ReBot improved the in-domain performance of Octo by 7.2% and OpenVLA by 21.8%, and out-of-domain generalization by 19.9% and 9.4%, respectively. For real-world evaluation with a Franka robot, ReBot increased the success rates of Octo by 17% and OpenVLA by 20%. More information can be found at our project page. Yue Yang 0024, Xinghao Zhu, Gedas Bertasius, Daniel Szafir, Mingyu Ding	IROS	7
2025	PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models abstract Robotic grasping, crucial for robot interaction with objects, still struggles with counter-intuitive or long-tailed scenarios like uncommon materials and shapes. Humans, however, intuitively adjust grasps with their physics-informed interpretations of the object, using visual and linguistic cues. This work introduces PhyGrasp, a large multimodal model and dataset that enhance robotic manipulation by combining natural language and 3D point clouds using a bridge module to integrate these inputs. The language modality exhibits robust reasoning capabilities concerning the impacts of diverse physical properties on grasping, while the 3D modality comprehends object shapes and parts. With these two capabilities, PhyGrasp is able to accurately assess the physical properties of object parts and determine optimal grasping poses. Additionally, the model’s language comprehension enables human instruction interpretation, generating grasping poses that align with human preferences. To train PhyGrasp, we construct a dataset PhyPartNet with 195K object instances with varying physical properties and human preferences, alongside their corresponding language descriptions. Extensive experiments conducted in the simulation and on the real robots demonstrate that PhyGrasp achieves state-of-the-art performance, particularly in long-tailed cases, e.g., about 10% improvement in success rate over GraspNet. More demos and information are available on https://sites.google.com/view/phygrasp. Dingkun Guo, Yuqi Xiang, Shuqi Zhao, Xinghao Zhu, Masayoshi Tomizuka, Mingyu Ding	IROS	6
2025	P2 Explore: Efficient Exploration in Unknown Cluttered Environment with Floor Plan Prediction abstract Robot exploration aims at the reconstruction of unknown environments, and it is important to achieve it with shorter paths. Traditional methods focus on optimizing the visiting order of frontiers based on current observations, which may lead to local-minimal results. Recently, by predicting the structure of the unseen environment, the exploration efficiency can be further improved. However, in a cluttered environment, due to the randomness of obstacles, the ability to predict is weak. Moreover, this inaccuracy will lead to limited improvement in exploration. Therefore, we propose FPUNet which can be efficient in predicting the layout of noisy indoor environments. Then, we extract the segmentation of rooms and construct their topological connectivity based on the predicted map. The visiting order of these predicted rooms is optimized which can provide high-level guidance for exploration. The FPUNet is compared with other network architectures which demonstrates it is the SOTA method for this task. Extensive experiments in simulations show that our method can shorten the path length by 2.18% to 34.60% compared to the baselines. Gaoming Chen, Masayoshi Tomizuka, Zhenhua Xiong 0001, Mingyu Ding	IROS	6
2025	MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference abstract Recent advancements in video generation have significantly improved the ability to synthesize videos from text instructions. However, existing models still struggle with key challenges such as instruction misalignment, content hallucination, safety concerns, and generation bias. To address these limitations, we introduce MJ-BENCH-VIDEO, a large-scale video preference benchmark designed to evaluate video generation across five critical aspects: Alignment, Safety, Fineness, Coherence & Consistency, and Bias & Fairness. This benchmark further incorporates 28 fine-grained criteria to provide a comprehensive evaluation of video preference. Building upon this dataset, we propose MJ-VIDEO, a Mixture-of-Experts (MoE)-based video reward model designed to deliver fine-grained reward. MJ-VIDEO can dynamically select relevant experts to accurately judge the preference based on the input text-video pair. This architecture enables more precise and adaptable preference judgments. Through extensive benchmarking on MJ-BENCH-VIDEO, we analyze the limitations of existing video reward models and demonstrate the superior performance of MJ-VIDEO in video preference assessment, achieving 17.58% and 15.87% improvements in overall and fine-grained preference judgments, respectively. Additionally, MJ-VIDEO is able to improve the alignment performance in video generation via preference fine-tuning. Haibo Tong, Zhaoyang Wang 0004, Zhaorun Chen, Haonian Ji, Shi Qiu 0016, Siwei Han, Kexin Geng, Zhongkai Xue, Yiyang Zhou, Peng Xia 0005, Mingyu Ding, Rafael Rafailov, Chelsea Finn, Huaxiu Yao	NeurIPS	11
2025	Compositional Physical Reasoning of Objects and Events From Videos abstract Understanding and reasoning about objects' physical properties in the natural world is a fundamental challenge in artificial intelligence. While some properties like colors and shapes can be directly observed, others, such as mass and electric charge, are hidden from the objects' visual appearance. This paper addresses the unique challenge of inferring these hidden physical properties from objects' motion and interactions and predicting corresponding dynamics based on the inferred physical properties. We first introduce the Compositional Physical Reasoning (ComPhy) dataset. For a given set of objects, ComPhy includes limited videos of them moving and interacting under different initial conditions. The model is evaluated based on its capability to unravel the compositional hidden properties, such as mass and charge, and use this knowledge to answer a set of questions. Besides the synthetic videos from simulators, we also collect a real-world dataset to show further test physical reasoning abilities of different models. We evaluate state-of-the-art video reasoning models on ComPhy and reveal their limited ability to capture these hidden properties, which leads to inferior performance. We also propose a novel neuro-symbolic framework, Physical Concept Reasoner (PCR), that learns and reasons about both visible and hidden physical properties from question answering. Leveraging an object-centric representation, PCR utilizes videos and the associated natural language to infer objects' physical properties without dense object annotations. Furthermore, It incorporates property-aware graph networks to approximate the dynamic interactions among objects. PCR also employs a semantic parser to convert questions into semantic programs, and a program executor to execute the programs based on the learned physical properties and dynamics. After training, PCR demonstrates remarkable capabilities. It can detect and associate objects across frames, ground visible and hidden physical properties, make future and counterfactual predictions, and utilize these extracted representations to answer challenging questions. We hope the proposed ComPhy dataset and the PCR model present a promising step towards more comprehensive physical reasoning in AI systems. Zhenfang Chen, Shilong Dong, Kexin Yi, Yunzhu Li, Mingyu Ding, Antonio Torralba 0001, Josh Tenenbaum, Chuang Gan 0001	IEEE Trans. Pattern Anal. Mach. Intell.	5
2025	Sel4FT: Annotation Selection for Pretraining-Finetuning With Distribution Shift abstract The pretraining-finetuning paradigm has become dominant in computer vision, yet strategically exploiting limited annotation budgets during finetuning remains unexplored. We introduce active finetuning-a novel task for selecting the most informative samples to annotate within this paradigm. We propose Sel4FT, a unified annotation selection framework that optimizes a parametric model in continuous feature space to identify a subset preserving the entire pool's distribution while maintaining diversity. To address distribution shifts from data augmentation, we develop Sel4FT++ with augmentation-aware selection mechanisms. We theoretically prove our approach minimizes the Earth Mover's Distance between selected subset and full data pool. Our framework eliminates iterative retraining and annotation process during selection, providing an efficient solution for real-world deployment. Extensive experiments on image classification, long-tailed recognition, and semantic segmentation demonstrate state-of-the-art performance with over $100\times$100× speedup compared to existing methods. Han Lu 0004, Yichen Xie 0002, Mingyu Ding, Xiaokang Yang 0001, Masayoshi Tomizuka, Junchi Yan	IEEE Trans. Pattern Anal. Mach. Intell.	3
2024	SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution abstract Diffusion models have demonstrated strong potential for robotic trajectory planning. However, generating coherent trajectories from high-level instructions remains challenging, especially for long-range composition tasks requiring multiple sequential skills. We propose SkillDiffuser, an end-to-end hierarchical planning framework integrating interpretable skill learning with conditional diffusion planning to address this problem. At the higher level, the skill abstraction module learns discrete, human-understandable skill representations from visual observations and language instructions. These learned skill embeddings are then used to condition the diffusion model to generate customized latent trajectories aligned with the skills. This allows generating diverse state trajectories that adhere to the learnable skills. By integrating skill learning with conditional trajectory generation, SkillDiffuser produces coherent behavior following abstract instructions across diverse tasks. Experiments on multitask robotic manipulation benchmarks like Meta-World and LOReL demonstrate state-of-the-art performance and human-interpretable skill representations from SkillDiffuser. More visualization results and information could be found on our website. Zhixuan Liang, Yao Mu 0001, Hengbo Ma, Masayoshi Tomizuka, Mingyu Ding, Ping Luo 0002	CVPR	5
2024	Tree-Planner: Efficient Close-loop Task Planning with Large Language Models abstract This paper studies close-loop task planning, which refers to the process of generating a sequence of skills (a plan) to accomplish a specific goal while adapting the plan based on real-time observations. Recently, prompting Large Language Models (LLMs) to generate actions iteratively has become a prevalent paradigm due to its superior performance and user-friendliness. However, this paradigm is plagued by two inefficiencies: high token consumption and redundant error correction, both of which hinder its scalability for large-scale testing and applications. To address these issues, we propose Tree-Planner, which reframes task planning with LLMs into three distinct phases: plan sampling, action tree construction, and grounded deciding. Tree-Planner starts by using an LLM to sample a set of potential plans before execution, followed by the aggregation of them to form an action tree. Finally, the LLM performs a top-down decision-making process on the tree, taking into account real-time environmental information. Experiments show that Tree-Planner achieves state-of-the-art performance while maintaining high efficiency. By decomposing LLM queries into a single plan-sampling call and multiple grounded-deciding calls, a considerable part of the prompt are less likely to be repeatedly consumed. As a result, token consumption is reduced by 92.2\% compared to the previously best-performing model. Additionally, by enabling backtracking on the action tree as needed, the correction process becomes more flexible, leading to a 40.5\% decrease in error corrections. Mengkang Hu, Yao Mu 0001, Xinmiao Yu, Mingyu Ding, Shiguang Wu 0004, Wenqi Shao, Qiguang Chen, Bin Wang 0034, Yu Qiao 0001, Ping Luo 0002	ICLR	4
2024	UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling abstract Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes unsustainable due to heavy computational and storage costs. This paper proposes UniAdapter, which unifies unimodal and multimodal adapters for parameter-efficient cross-modal adaptation on pre-trained vision-language models. Specifically, adapters are distributed to different modalities and their interactions, with the total number of tunable parameters reduced by partial weight sharing. The unified and knowledge-sharing design enables powerful cross-modal representations that can benefit various downstream tasks, requiring only 1.0%-2.0% tunable parameters of the pre-trained model. Extensive experiments on 7 cross-modal downstream benchmarks (including video-text retrieval, image-text retrieval, VideoQA, VQA and Caption) show that in most cases, UniAdapter not only outperforms the state-of-the-arts, but even beats the full fine-tuning strategy. Particularly, on the MSRVTT retrieval task, UniAdapter achieves 49.7% recall@1 with 2.2% model parameters, outperforming the latest competitors by 2.0%. The code and models are available at https://github.com/RERV/UniAdapter. Haoyu Lu, Yuqi Huo, Guoxing Yang, Zhiwu Lu 0001, Masayoshi Tomizuka, Mingyu Ding	ICLR	7
2024	VDT: General-purpose Video Diffusion Transformers via Mask Modeling abstract This work introduces Video Diffusion Transformer (VDT), which pioneers the use of transformers in diffusion-based video generation. It features transformer blocks with modularized temporal and spatial attention modules to leverage the rich spatial-temporal representation inherited in transformers. Additionally, we propose a unified spatial-temporal mask modeling mechanism, seamlessly integrated with the model, to cater to diverse video generation scenarios. VDT offers several appealing benefits. (1) It excels at capturing temporal dependencies to produce temporally consistent video frames and even simulate the physics and dynamics of 3D objects over time. (2) It facilitates flexible conditioning information, e.g., simple concatenation in the token space, effectively unifying different token lengths and modalities. (3) Pairing with our proposed spatial-temporal mask modeling mechanism, it becomes a general-purpose video diffuser for harnessing a range of tasks, including unconditional generation, video prediction, interpolation, animation, and completion, etc. Extensive experiments on these tasks spanning various scenarios, including autonomous driving, natural weather, human action, and physics-based simulation, demonstrate the effectiveness of VDT. Moreover, we provide a comprehensive study on the capabilities of VDT in capturing accurate temporal dependencies, handling conditioning information, and the spatial-temporal mask modeling mechanism. Additionally, we present comprehensive studies on how VDT handles conditioning information with the mask modeling mechanism, which we believe will benefit future research and advance the field. Codes and models are available at the https://VDT-2023.github.io. Haoyu Lu, Guoxing Yang, Nanyi Fei, Yuqi Huo, Zhiwu Lu 0001, Ping Luo 0002, Mingyu Ding	ICLR	7
2024	RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis abstract Robotic behavior synthesis, the problem of understanding multimodal inputs and generating precise physical control for robots, is an important part of Embodied AI. Despite successes in applying multimodal large language models for high-level understanding, it remains challenging to translate these conceptual understandings into detailed robotic actions while achieving generalization across various scenarios. In this paper, we propose a tree-structured multimodal code generation framework for generalized robotic behavior synthesis, termed RoboCodeX. RoboCodeX decomposes high-level human instructions into multiple object-centric manipulation units consisting of physical preferences such as affordance and safety constraints, and applies code generation to introduce generalization ability across various robotics platforms. To further enhance the capability to map conceptual and perceptual understanding into control commands, a specialized multimodal reasoning dataset is collected for pre-training and an iterative self-updating methodology is introduced for supervised fine-tuning. Extensive experiments demonstrate that RoboCodeX achieves state-of-the-art performance in both simulators and real robots on four different kinds of manipulation tasks and one embodied navigation task. Yao Mu 0001, Shoufa Chen, Qiaojun Yu, Chongjian Ge, Runjian Chen, Zhixuan Liang, Mengkang Hu, Chaofan Tao, Peize Sun, Haibao Yu, Chao Yang 0026, Wenqi Shao, Wenhai Wang, Jifeng Dai, Yu Qiao 0001, Mingyu Ding, Ping Luo 0002	ICML	18
2024	Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration abstract Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io. Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin	ICRA	161
2024	Pre-training on Synthetic Driving Data for Trajectory Prediction abstract Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim to tackle the challenge of learning general trajectory forecasting representations under limited data availability. We propose a pipeline-level solution to mitigate the issue of data scarcity in trajectory forecasting. The solution is composed of two parts: firstly, we adopt HD map augmentation and trajectory synthesis for generating driving data, and then we learn representations by pre-training on them. Specifically, we apply vector transformations to reshape the maps, and then employ a rule-based model to generate trajectories on both original and augmented scenes; thus enlarging the driving data without collecting additional real ones. To foster the learning of general representations within this augmented dataset, we comprehensively explore the different pre-training strategies, including extending the concept of a Masked AutoEncoder (MAE) for trajectory forecasting. Without bells and whistles, our proposed pipeline-level solution is general, simple, yet effective: we conduct extensive experiments to demonstrate the effectiveness of our data expansion and pre-training strategies, which outperform the baseline prediction model by large margins, e.g. 5.04%, 3.84% and 8.30% in terms of MR6, minADE6and minFDE6. The pre-training dataset and the codes for pre-training and fine-tuning are released at https://github.com/yhli123/Pretraining_on_Synthetic_Driving_Data_for_Trajectory_Prediction. Seth Z. Zhao, Chenfeng Xu, Chen Tang 0001, Chenran Li, Mingyu Ding, Masayoshi Tomizuka	IROS	6
2024	DSLO: Deep Sequence LiDAR Odometry Based on Inconsistent Spatio-temporal Propagation abstract This paper introduces a 3D point cloud sequence learning model based on inconsistent spatio-temporal propagation for LiDAR odometry, termed DSLO. It consists of a pyramid structure with a spatial information reuse strategy, a sequential pose initialization module, a gated hierarchical pose refinement module, and a temporal feature propagation module. First, spatial features are encoded using a point feature pyramid, with features reused in successive pose estimations to reduce computational overhead. Second, a sequential pose initialization method is introduced, leveraging the high-frequency sampling characteristic of LiDAR to initialize the LiDAR pose. Then, a gated hierarchical pose refinement mechanism refines poses from coarse to fine by selectively retaining or discarding motion information from different layers based on gate estimations. Finally, temporal feature propagation is proposed to incorporate the historical motion information from point cloud sequences, and address the spatial inconsistency issue when transmitting motion information embedded in point clouds between frames. Experimental results on the KITTI odometry dataset and Argoverse dataset demonstrate that DSLO outperforms state-of-the-art methods, achieving at least a 15.67% improvement on RTE and a 12.64% improvement on RRE, while also achieving a 34.69% reduction in runtime compared to baseline methods. Our implementation will be available at https://github.com/IRMVLab/DSLO. Guangming Wang 0001, Xinrui Wu, Chenfeng Xu, Mingyu Ding, Masayoshi Tomizuka, Hesheng Wang 0001	IROS	5
2024	MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts abstract Text-to-image diffusion has attracted vast attention due to its impressive image-generation capabilities. However, when it comes to human-centric text-to-image generation, particularly in the context of faces and hands, the results often fall short of naturalness due to insufficient training priors. We alleviate the issue in this work from two perspectives. 1) From the data aspect, we carefully collect a human-centric dataset comprising over one million high-quality human-in-the-scene images and two specific sets of close-up images of faces and hands. These datasets collectively provide a rich prior knowledge base to enhance the human-centric image generation capabilities of the diffusion model. 2) On the methodological front, we propose a simple yet effective method called Mixture of Low-rank Experts (MoLE) by considering low-rank modules trained on close-up hand and face images respectively as experts. This concept draws inspiration from our observation of low-rank refinement, where a low-rank module trained by a customized close-up dataset has the potential to enhance the corresponding image part when applied at an appropriate scale. To validate the superiority of MoLE in the context of human-centric image generation compared to state-of-the-art, we construct two benchmarks and perform evaluations with diverse metrics and human studies. Datasets, model, and code are released at https://sites.google.com/view/mole4diffuser/. Yixiong Chen, Mingyu Ding, Ping Luo 0002, Leye Wang, Jingdong Wang 0001	NeurIPS	3
2024	Interfacing Foundation Models' Embeddings abstract Foundation models possess strong capabilities in reasoning and memorizing across modalities. To further unleash the power of foundation models, we present FIND, a generalized interface for aligning foundation models' embeddings with unified image and dataset-level understanding spanning modality and granularity. As shown in Fig.1, a lightweight transformer interface without tuning any foundation model weights is enough for segmentation, grounding, and retrieval in an interleaved manner. The proposed interface has the following favorable attributes: (1) Generalizable. It applies to various tasks spanning retrieval, segmentation, etc., under the same architecture and weights. (2) Interleavable. With the benefit of multi-task multi-modal training, the proposed interface creates an interleaved shared embedding space. (3) Extendable. The proposed interface is adaptive to new tasks, and new models. In light of the interleaved embedding space, we introduce FIND-Bench, which introduces new training and evaluation annotations to the COCO dataset for interleaved segmentation and retrieval. We are the first work aligning foundations models' embeddings for interleave understanding. Meanwhile, our approach achieves state-of-the-art performance on FIND-Bench and competitive performance on standard retrieval and segmentation settings. Xueyan Zou, Mingyu Ding, Zhengyuan Yang, Feng Li 0040, Hao Zhang 0097, Shilong Liu 0004, Arul Aravinthan, Yong Jae Lee	NeurIPS	5
2024	Context Autoencoder for Self-supervised Representation Learning Xiaokang Chen, Mingyu Ding, Shentong Mo, Shumin Han, Ping Luo 0002, Jingdong Wang 0001	Int. J. Comput. Vis.	2
2024	RoadBEV: Road Surface Reconstruction in Bird's Eye View abstract Road surface conditions, especially geometry profiles, enormously affect driving performance of autonomous vehicles. Vision-based online road reconstruction promisingly captures road information in advance. Existing solutions like monocular depth estimation and stereo matching suffer from modest performance. The recent technique of Bird’s-Eye-View (BEV) perception provides immense potential to more reliable and accurate reconstruction. This paper uniformly proposes two simple yet effective models for road elevation reconstruction in BEV named RoadBEV-mono and RoadBEV-stereo, which estimate road elevation with monocular and stereo images, respectively. The former directly fits elevation values based on voxel features queried from image view, while the latter efficiently recognizes road elevation patterns based on BEV volume representing correlation between left and right voxel features. Insightful analyses reveal their consistence and difference with the perspective view. Experiments on real-world dataset verify the models’ effectiveness and superiority. Elevation errors of RoadBEV-mono and RoadBEV-stereo achieve 1.83 cm and 0.50 cm, respectively. Our models are promising for practical road preview, providing essential information for promoting safety and comfort of autonomous vehicles. The code is released athttps://github.com/ztsrxh/RoadBEV. Lei Yang 0060, Yichen Xie 0002, Mingyu Ding, Masayoshi Tomizuka, Yintao Wei	IEEE Trans. Intell. Transp. Syst.	4
2023	Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners abstract Optimization in multi-task learning (MTL) is more challenging than single-task learning (STL), as the gradient from different tasks can be contradictory. When tasks are related, it can be beneficial to share some parameters among them (cooperation). However, some tasks require additional parameters with expertise in a specific type of data or discrimination (specialization). To address the MTL challenge, we propose Mod-Squad, a new model that is Modularized into groups of experts (a ‘Squad’). This structure allows us to formalize cooperation and specialization as the process of matching experts and tasks. We optimize this matching process during the training of a single model. Specifically, we incorporate mixture of experts (MoE) layers into a transformer model, with a new loss that incorporates the mutual dependence between tasks and experts. As a result, only a small set of experts are activated for each task. This prevents the sharing of the entire backbone model between all tasks, which strengthens the model, especially when the training set size and the number of tasks scale up. More interestingly, for each task, we can extract the small set of experts as a standalone model that maintains the same performance as the large model. Extensive experiments on the Taskonomy dataset with 13 vision tasks and the PASCAL-Context dataset with 5 vision tasks show the superiority of our approach. The project page can be accessed at https://vis-www.cs.umass.edu/Mod-Squad. Zitian Chen, Yikang Shen, Mingyu Ding, Zhenfang Chen, Hengshuang Zhao, Erik G. Learned-Miller, Chuang Gan 0001	CVPR	3
2023	Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention abstract Humans possess a versatile mechanism for extracting structured representations of our visual world. When looking at an image, we can decompose the scene into entities and their parts as well as obtain the dependencies between them. To mimic such capability, we propose Visual Dependency Transformers (DependencyViT)11https://github.com/dingmyu/DependencyViT that can induce visual dependencies without any labels. We achieve that with a novel neural operator called reversed attention that can naturally capture long-range visual dependencies between image patches. Specifically, we formulate it as a dependency graph where a child token in reversed attention is trained to attend to its parent tokens and send information following a normalized probability distribution rather than gathering information in conventional self-attention. With such a design, hierarchies naturally emerge from reversed attention layers, and a dependency tree is progressively induced from leaf nodes to the root node unsupervisedly. DependencyViT offers several appealing benefits. (i) Entities and their parts in an image are represented by different subtrees, enabling part partitioning from dependencies; (ii) Dynamic visual pooling is made possible. The leaf nodes which rarely send messages can be pruned without hindering the model performance, based on which we propose the lightweight DependencyViT-Lite to reduce the computational and memory footprints; (iii) DependencyViT works well on both self- and weakly-supervised pretraining paradigms on ImageNet, and demonstrates its effectiveness on 8 datasets and 5 tasks, such as unsupervised part and saliency segmentation, recognition, and detection. Mingyu Ding, Yikang Shen, Lijie Fan, Zhenfang Chen, Zitian Chen, Ping Luo 0002, Josh Tenenbaum, Chuang Gan 0001	CVPR	1
2023	EC2: Emergent Communication for Embodied Control abstract Embodied control requires agents to leverage multimodal pre-training to quickly learn how to act in new environments, where video demonstrations contain visual and motion details needed for low-level perception and control, and language instructions support generalization with abstract, symbolic structures. While recent approaches apply contrastive learning to force alignment between the two modalities, we hypothesize better modeling their complementary differences can lead to more holistic representations for downstream adaption. To this end, we propose Emergent Communication for Embodied Control (EC2), a novel scheme to pre-train video-language representations for few-shot embodied control. The key idea is to learn an unsupervised “language” of videos via emergent communication, which bridges the semantics of video details and structures of natural language. We learn embodied representations of video trajectories, emergent language, and natural language using a language model, which is then used to finetune a lightweight policy network for downstream control. Through extensive experiments in Metaworld and Franka Kitchen embodied benchmarks, EC2is shown to consistently outperform previous contrastive learning methods for both videos and texts as task inputs. Further ablations confirm the importance of the emergent language, which is beneficial for both video and language learning, and significantly superior to using pre-trained video captions. We also present a quantitative and qualitative analysis of the emergent language and discuss future directions toward better understanding and leveraging emergent communication in embodied tasks. Yao Mu 0001, Shunyu Yao 0006, Mingyu Ding, Ping Luo 0002, Chuang Gan 0001	CVPR	3
2023	TextPSG: Panoptic Scene Graph Generation from Textual Descriptions abstract Panoptic Scene Graph has recently been proposed for comprehensive scene understanding. However, previous works adopt a fully-supervised learning manner, requiring large amounts of pixel-wise densely-annotated data, which is always tedious and expensive to obtain. To address this limitation, we study a new problem of Panoptic Scene Graph Generation from Purely Textual Descriptions (Caption-to-PSG). The key idea is to leverage the large collection of free image-caption data on the Web alone to generate panoptic scene graphs. The problem is very challenging for three constraints: 1) no location priors; 2) no explicit links between visual regions and textual entities; and 3) no predefined concept sets. To tackle this problem, we propose a new framework TextPSG consisting of four modules, i.e., a region grouper, an entity grounder, a segment merger, and a label generator, with several novel techniques. The region grouper first groups image pixels into different segments and the entity grounder then aligns visual segments with language entities based on the textual description of the segment being referred to. The grounding results can thus serve as pseudo labels enabling the segment merger to learn the segment similarity as well as guiding the label generator to learn object semantics and relation predicates, resulting in a fine-grained structured scene understanding. Our framework is effective, significantly outperforming the baselines and achieving strong out-of-distribution robustness. We perform comprehensive ablation studies to corroborate the effectiveness of our design choices and provide an in-depth analysis to highlight future directions. Our code, data, and results are available on our project page: https://vis-www.cs.umass.edu/TextPSG. Chengyang Zhao, Yikang Shen, Zhenfang Chen, Mingyu Ding, Chuang Gan 0001	ICCV	4
2023	Planning with Large Language Models for Code Generation Zhenfang Chen, Yikang Shen, Mingyu Ding, Josh Tenenbaum, Chuang Gan 0001	ICLR	4
2023	AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners abstract Diffusion models have demonstrated their powerful generative capability in many tasks, with great potential to serve as a paradigm for offline reinforcement learning. However, the quality of the diffusion model is limited by the insufficient diversity of training data, which hinders the performance of planning and the generalizability to new tasks. This paper introduces AdaptDiffuser, an evolutionary planning method with diffusion that can self-evolve to improve the diffusion model hence a better planner, not only for seen tasks but can also adapt to unseen tasks. AdaptDiffuser enables the generation of rich synthetic expert data for goal-conditioned tasks using guidance from reward gradients. It then selects high-quality data via a discriminator to finetune the diffusion model, which improves the generalization ability to unseen tasks. Empirical experiments on two benchmark environments and two carefully designed unseen tasks in KUKA industrial robot arm and Maze2D environments demonstrate the effectiveness of AdaptDiffuser. For example, AdaptDiffuser not only outperforms the previous art Diffuser by 20.8% on Maze2D and 7.5% on MuJoCo locomotion, but also adapts better to new tasks, e.g., KUKA pick-and-place, by 27.9% without requiring additional expert data. More visualization results and demo videos could be found on our project page. Zhixuan Liang, Yao Mu 0001, Mingyu Ding, Fei Ni 0001, Masayoshi Tomizuka, Ping Luo 0002	ICML	3
2023	EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought abstract Embodied AI is a crucial frontier in robotics, capable of planning and executing action sequences for robots to accomplish long-horizon tasks in physical environments. In this work, we introduce EmbodiedGPT, an end-to-end multi-modal foundation model for embodied AI, empowering embodied agents with multi-modal understanding and execution capabilities. To achieve this, we have made the following efforts: (i) We craft a large-scale embodied planning dataset, termed EgoCOT. The dataset consists of carefully selected videos from the Ego4D dataset, along with corresponding high-quality language instructions. Specifically, we generate a sequence of sub-goals with the "Chain of Thoughts" mode for effective embodied planning. (ii) We introduce an efficient training approach to EmbodiedGPT for high-quality plan generation, by adapting a 7B large language model (LLM) to the EgoCOT dataset via prefix tuning. (iii) We introduce a paradigm for extracting task-related features from LLM-generated planning queries to form a closed loop between high-level planning and low-level control. Extensive experiments show the effectiveness of EmbodiedGPT on embodied tasks, including embodied planning, embodied control, visual captioning, and visual question answering. Notably, EmbodiedGPT significantly enhances the success rate of the embodied control task by extracting more effective features. It has achieved a remarkable 1.6 times increase in success rate on the Franka Kitchen benchmark and a 1.3 times increase on the Meta-World benchmark, compared to the BLIP-2 baseline fine-tuned with the Ego4D dataset. Yao Mu 0001, Mengkang Hu, Wenhai Wang, Mingyu Ding, Bin Wang 0034, Jifeng Dai, Yu Qiao 0001, Ping Luo 0002	NeurIPS	5
2023	Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties abstract General physical scene understanding requires more than simply localizing and recognizing objects -- it requires knowledge that objects can have different latent properties (e.g., mass or elasticity), and that those properties affect the outcome of physical events. While there has been great progress in physical and video prediction models in recent years, benchmarks to test their performance typically do not require an understanding that objects have individual physical properties, or at best test only those properties that are directly observable (e.g., size or color). This work proposes a novel dataset and benchmark, termed Physion++, that rigorously evaluates visual physical prediction in artificial systems under circumstances where those predictions rely on accurate estimates of the latent physical properties of objects in the scene. Specifically, we test scenarios where accurate prediction relies on estimates of properties such as mass, friction, elasticity, and deformability, and where the values of those properties can only be inferred by observing how objects move and interact with other objects or fluids. We evaluate the performance of a number of state-of-the-art prediction models that span a variety of levels of learning vs. built-in knowledge, and compare that performance to a set of human predictions. We find that models that have been trained using standard regimes and datasets do not spontaneously learn to make inferences about latent properties, but also that models that encode objectness and physical states tend to make better predictions. However, there is still a huge gap between all models and human performance, and all models' predictions correlate poorly with those made by humans, suggesting that no state-of-the-art model is learning to make physical predictions in a human-like way. These results show that current deep learning models that succeed in some settings nevertheless fail to achieve human-level physical prediction in other cases, especially those where latent property inference is required. Project page: https://dingmyu.github.io/physion_v2/ Hsiao-Yu Fish Tung, Mingyu Ding, Zhenfang Chen, Daniel Bear, Chuang Gan 0001, Josh Tenenbaum, Dan Yamins, Judith E. Fan, Kevin A. Smith 0001	NeurIPS	2
2023	Towards Free Data Selection with General-Purpose Models abstract A desirable data selection algorithm can efficiently choose the most informative samples to maximize the utility of limited annotation budgets. However, current approaches, represented by active learning methods, typically follow a cumbersome pipeline that iterates the time-consuming model training and batch data selection repeatedly. In this paper, we challenge this status quo by designing a distinct data selection pipeline that utilizes existing general-purpose models to select data from various datasets with a single-pass inference without the need for additional training or supervision. A novel free data selection (FreeSel) method is proposed following this new pipeline. Specifically, we define semantic patterns extracted from inter-mediate features of the general-purpose model to capture subtle local information in each image. We then enable the selection of all data samples in a single pass through distance-based sampling at the fine-grained semantic pattern level. FreeSel bypasses the heavy batch selection process, achieving a significant improvement in efficiency and being 530x faster than existing active learning methods. Extensive experiments verify the effectiveness of FreeSel on various computer vision tasks. Yichen Xie 0002, Mingyu Ding, Masayoshi Tomizuka	NeurIPS	2
2023	Doubly-Robust Self-Training abstract Self-training is a well-established technique in semi-supervised learning, which leverages unlabeled data by generating pseudo-labels and incorporating them with a limited labeled dataset for training. The effectiveness of self-training heavily relies on the accuracy of these pseudo-labels. In this paper, we introduce doubly-robust self-training, an innovative semi-supervised algorithm that provably balances between two extremes. When pseudo-labels are entirely incorrect, our method reduces to a training process solely using labeled data. Conversely, when pseudo-labels are completely accurate, our method transforms into a training process utilizing all pseudo-labeled data and labeled data, thus increasing the effective sample size. Through empirical evaluations on both the ImageNet dataset for image classification and the nuScenes autonomous driving dataset for 3D object detection, we demonstrate the superiority of the doubly-robust loss over the self-training baseline. Banghua Zhu, Mingyu Ding, Philip L. Jacobson, Michael I. Jordan, Jiantao Jiao	NeurIPS	2
2022	DaViT: Dual Attention Vision Transformers Mingyu Ding, Bin Xiao 0004, Noel Codella, Ping Luo 0002, Jingdong Wang 0001, Lu Yuan 0001	ECCV (24)	1
2022	ComPhy: Compositional Physical Reasoning of Objects and Events from Videos Zhenfang Chen, Kexin Yi, Yunzhu Li, Mingyu Ding, Antonio Torralba 0001, Josh Tenenbaum, Chuang Gan 0001	ICLR	4
2022	Learning Versatile Neural Architectures by Propagating Network Codes Mingyu Ding, Yuqi Huo, Haoyu Lu, Zhe Wang 0006, Zhiwu Lu 0001, Jingdong Wang 0001, Ping Luo 0002	ICLR	1
2022	CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer abstract Transformer has achieved great successes in learning vision and language representation, which is general across various downstream tasks. In visual control, learning transferable state representation that can transfer between different control tasks is important to reduce the training sample size. However, porting Transformer to sample-efficient visual control remains a challenging and unsolved problem. To this end, we propose a novel Control Transformer (CtrlFormer), possessing many appealing benefits that prior arts do not have. Firstly, CtrlFormer jointly learns self-attention mechanisms between visual tokens and policy tokens among different control tasks, where multitask representation can be learned and transferred without catastrophic forgetting. Secondly, we carefully design a contrastive reinforcement learning paradigm to train CtrlFormer, enabling it to achieve high sample efficiency, which is important in control problems. For example, in the DMControl benchmark, unlike recent advanced methods that failed by producing a zero score in the “Cartpole” task after transfer learning with 100k samples, CtrlFormer can achieve a state-of-the-art score with only 100k samples while maintaining the performance of previous tasks. The code and models are released in our project homepage. Yao Mu 0001, Shoufa Chen, Mingyu Ding, Jianyu Chen 0002, Runjian Chen, Ping Luo 0002	ICML	3
2022	LGDN: Language-Guided Denoising Network for Video-Language Modeling abstract Video-language modeling has attracted much attention with the rapid growth of web videos. Most existing methods assume that the video frames and text description are semantically correlated, and focus on video-language modeling at video level. However, this hypothesis often fails for two reasons: (1) With the rich semantics of video contents, it is difficult to cover all frames with a single video-level description; (2) A raw video typically has noisy/meaningless information (e.g., scenery shot, transition or teaser). Although a number of recent works deploy attention mechanism to alleviate this problem, the irrelevant/noisy information still makes it very difficult to address. To overcome such challenge, we thus propose an efficient and effective model, termed Language-Guided Denoising Network (LGDN), for video-language modeling. Different from most existing methods that utilize all extracted video frames, LGDN dynamically filters out the misaligned or redundant frames under the language supervision and obtains only 2--4 salient frames per video for cross-modal token-level alignment. Extensive experiments on five public datasets show that our LGDN outperforms the state-of-the-arts by large margins. We also provide detailed ablation study to reveal the critical importance of solving the noise issue, in hope of inspiring future video-language work. Haoyu Lu, Mingyu Ding, Nanyi Fei, Yuqi Huo, Zhiwu Lu 0001	NeurIPS	2
2022	PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond abstract Reducing complexity of the pipeline of instance segmentation is crucial for real-world applications. This work addresses this problem by introducing an anchor-box free and single-shot instance segmentation framework, termed PolarMask++, which reformulates the instance segmentation problem as predicting the contours of objects in the polar coordinate, leading to several appealing benefits. (1) The polar representation unifies instance segmentation (masks) and object detection (bounding boxes) into a single framework, reducing the design and computational complexity. (2) We carefully design two modules (soft polar centerness and polar IoU loss) to sample high-quality center examples and optimize polar contour regression, making the performance of PolarMask++ does not depend on the bounding box prediction and thus more efficient in training. (3) PolarMask++ is fully convolutional and can be easily embedded into most off-the-shelf detectors. To further improve the accuracy of the framework, a Refined Feature Pyramid is introduced to improve the feature representation at different scales. Extensive experiments demonstrate the effectiveness of PolarMask++, which achieves competitive results on COCO dataset, and new state-of-the-art results on text detection and cell segmentation datasets. We hope polar representation can provide a new perspective for designing algorithms to solve single-shot instance segmentation. Code is released at: github.com/xieenze/PolarMask. Enze Xie, Wenhai Wang, Mingyu Ding, Ruimao Zhang, Ping Luo 0002	IEEE Trans. Pattern Anal. Mach. Intell.	3
2021	A Global Occlusion-Aware Approach to Self-Supervised Monocular Visual Odometry abstract Self-Supervised monocular visual odometry (VO) is often cast into a view synthesis problem based on depth and camera pose estimation. One of the key challenges is to accurately and robustly estimate depth with occlusions and moving objects in the scene. Existing methods simply detect and mask out regions of occlusions locally by several convolutional layers, and then perform only partial view synthesis in the rest of the image. However, occlusion and moving object detection is an unsolved problem itself which requires global layout information. Inaccurate detection inevitably results in incorrect depth as well as pose estimation. In this work, instead of locally detecting and masking out occlusions and moving objects, we propose to alleviate their negative effects on monocular VO implicitly but more effectively from two global perspectives. First, a multi-scale non-local attention module, consisting of both intra-stage augmented attention and cascaded across-stage attention, is proposed for robust depth estimation given occlusions, alleviating the impacts of occlusions via global attention modeling. Second, adversarial learning is introduced in view synthesis for monocular VO. Unlike existing methods that use pixel-level losses on the quality of synthesized views, we enforce the synthetic view to be indistinguishable from the real one at the scene-level. Such a global constraint again helps cope with occluded and moving regions. Extensive experiments on the KITTI dataset show that our approach achieves new state-of-the-art in both pose estimation and depth recovery. Xiaoli Xu 0003, Mingyu Ding, Zhiwu Lu 0001, Tao Xiang 0002	AAAI	3
2021	HR-NAS: Searching Efficient High-Resolution Neural Architectures With Lightweight Transformers abstract High-resolution representations (HR) are essential for dense prediction tasks such as segmentation, detection, and pose estimation. Learning HR representations is typically ignored in previous Neural Architecture Search (NAS) methods that focus on image classification. This work proposes a novel NAS method, called HR-NAS, which is able to find efficient and accurate networks for different tasks, by effectively encoding multiscale contextual information while maintaining high-resolution representations. In HR-NAS, we renovate the NAS search space as well as its searching strategy. To better encode multiscale image contexts in the search space of HR-NAS, we first carefully design a lightweight transformer, whose computational complexity can be dynamically changed with respect to different objective functions and computation budgets. To maintain high-resolution representations of the learned networks, HR-NAS adopts a multi-branch architecture that provides convolutional encoding of multiple feature resolutions, inspired by HRNet [73]. Last, we proposed an efficient fine-grained search strategy to train HR-NAS, which effectively explores the search space, and finds optimal architectures given various tasks and computation resources. As shown in Fig. 1 (a), HR-NAS is capable of achieving state-of-the-art trade-offs between performance and FLOPs for three dense prediction tasks and an image classification task, given only small computational budgets. For example, HR-NAS surpasses SqueezeNAS [63] that is specially designed for semantic segmentation while improving efficiency by 45.9%. Code is available at https://github.com/dingmyu/HR-NAS. Mingyu Ding, Xiaochen Lian, Peng Wang 0037, Xiaojie Jin 0004, Zhiwu Lu 0001, Ping Luo 0002	CVPR	1
2021	L2M-GAN: Learning To Manipulate Latent Space Semantics for Facial Attribute Editing abstract A deep facial attribute editing model strives to meet two requirements: (1) attribute correctness – the target attribute should correctly appear on the edited face image; (2) irrelevance preservation – any irrelevant information (e.g., identity) should not be changed after editing. Meeting both requirements challenges the state-of-the-art works which resort to either spatial attention or latent space factorization. Specifically, the former assume that each attribute has well-defined local support regions; they are often more effective for editing a local attribute than a global one. The latter factorize the latent space of a fixed pretrained GAN into different attribute-relevant parts, but they cannot be trained end-to-end with the GAN, leading to sub-optimal solutions. To overcome these limitations, we propose a novel latent space factorization model, called L2M-GAN, which is learned end-to-end and effective for editing both local and global attributes. The key novel components are: (1) A latent space vector of the GAN is factorized into an attribute-relevant and irrelevant codes with an orthogonality constraint imposed to ensure disentanglement. (2) An attribute-relevant code transformer is learned to manipulate the attribute value; crucially, the transformed code are subject to the same orthogonality constraint. By forcing both the original attribute-relevant latent code and the edited code to be disentangled from any attribute-irrelevant code, our model strikes the perfect balance between attribute correctness and irrelevance preservation. Extensive experiments on CelebA-HQ show that our L2M-GAN achieves significant improvements over the state-of-the-arts. Guoxing Yang, Nanyi Fei, Mingyu Ding, Guangzhen Liu, Zhiwu Lu 0001, Tao Xiang 0002	CVPR	3
2021	IEPT: Instance-Level and Episode-Level Pretext Tasks for Few-Shot Learning Manli Zhang, Zhiwu Lu 0001, Tao Xiang 0002, Mingyu Ding, Songfang Huang	ICLR	5
2021	Self-Supervised Video Representation Learning with Constrained Spatiotemporal Jigsaw abstract This paper proposes a novel pretext task for self-supervised video representation learning by exploiting spatiotemporal continuity in videos. It is motivated by the fact that videos are spatiotemporal by nature and a representation learned by detecting spatiotemporal continuity/discontinuity is thus beneficial for downstream video content analysis tasks. A natural choice of such a pretext task is to construct spatiotemporal (3D) jigsaw puzzles and learn to solve them. However, as we demonstrate in the experiments, this task turns out to be intractable. We thus propose Constrained Spatiotemporal Jigsaw (CSJ) whereby the 3D jigsaws are formed in a constrained manner to ensure that large continuous spatiotemporal cuboids exist. This provides sufficient cues for the model to reason about the continuity. Instead of solving them directly, which could still be extremely hard, we carefully design four surrogate tasks that are more solvable. The four tasks aim to learn representations sensitive to spatiotemporal continuity at both the local and global levels. Extensive experiments show that our CSJ achieves state-of-the-art on various benchmarks. Yuqi Huo, Mingyu Ding, Haoyu Lu, Mingqian Tang, Zhiwu Lu 0001, Tao Xiang 0002	IJCAI	2
2021	Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language abstract In this work, we propose a unified framework, called Visual Reasoning with Differ-entiable Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects and their interactions from videos and language. This is achieved by seamlessly integrating three components: a visual perception module, a concept learner, and a differentiable physics engine. The visual perception module parses each video frame into object-centric trajectories and represents them as latent scene representations. The concept learner grounds visual concepts (e.g., color, shape, and material) from these object-centric representations based on the language, thus providing prior knowledge for the physics engine. The differentiable physics model, implemented as an impulse-based differentiable rigid-body simulator, performs differentiable physical simulation based on the grounded concepts to infer physical properties, such as mass, restitution, and velocity, by fitting the simulated trajectories into the video observations. Consequently, these learned concepts and physical models can explain what we have seen and imagine what is about to happen in future and counterfactual scenarios. Integrating differentiable physics into the dynamic reasoning framework offers several appealing benefits. More accurate dynamics prediction in learned physics models enables state-of-the-art performance on both synthetic and real-world benchmarks while still maintaining high transparency and interpretability; most notably, VRDP improves the accuracy of predictive and counterfactual questions by 4.5% and 11.5% compared to its best counterpart. VRDP is also highly data-efficient: physical parameters can be optimized from very few videos, and even a single video can be sufficient. Finally, with all physical parameters inferred, VRDP can quickly learn new concepts from a few examples. Mingyu Ding, Zhenfang Chen, Tao Du 0001, Ping Luo 0002, Josh Tenenbaum, Chuang Gan 0001	NeurIPS	1
2021	Compressed Video Contrastive Learning abstract This work concerns self-supervised video representation learning (SSVRL), one topic that has received much attention recently. Since videos are storage-intensive and contain a rich source of visual content, models designed for SSVRL are expected to be storage- and computation-efficient, as well as effective. However, most existing methods only focus on one of the two objectives, failing to consider both at the same time. In this work, for the first time, the seemingly contradictory goals are simultaneously achieved by exploiting compressed videos and capturing mutual information between two input streams. Specifically, a novel Motion Vector based Cross Guidance Contrastive learning approach (MVCGC) is proposed. For storage and computation efficiency, we choose to directly decode RGB frames and motion vectors (that resemble low-resolution optical flows) from compressed videos on-the-fly. To enhance the representation ability of the motion vectors, hence the effectiveness of our method, we design a cross guidance contrastive learning algorithm based on multi-instance InfoNCE loss, where motion vectors can take supervision signals from RGB frames and vice versa. Comprehensive experiments on two downstream tasks show that our MVCGC yields new state-of-the-art while being significantly more efficient than its competitors. Yuqi Huo, Mingyu Ding, Haoyu Lu, Nanyi Fei, Zhiwu Lu 0001, Ji-Rong Wen, Ping Luo 0002	NeurIPS	2
2021	Domain-Adaptive Few-Shot Learning abstract Existing few-shot learning (FSL) methods make the implicit assumption that the few target class samples are from the same domain as the source class samples. However, in practice, this assumption is often invalid -the target classes could come from a different domain. This poses an additional challenge of domain adaptation (DA) with few training samples. In this paper, the problem of domain-adaptive few-shot learning (DA-FSL) is tackled, which is expected to have wide use in real-world scenarios and requires solving FSL and DA in a unified framework. To this end, we propose a novel domain-adversarial prototypical network (DAPN) model. It is designed to address a specific challenge in DA-FSL: the DA objective means that the source and target data distributions need to be aligned, typically through a shared domain-adaptive feature embedding space; but the FSL objective dictates that the target domain per class distribution must be different from that of any source domain class, meaning aligning the distributions across domains may harm the FSL performance. How to achieve global domain distribution alignment whilst maintaining source/target per-class discriminativeness thus becomes the key. Our solution is to explicitly enhance the source/target per-class separation before domain-adaptive feature embedding learning, to alleviate the negative effect of domain alignment on FSL. Extensive experiments show that our DAPN outperforms the state-of-the-arts. The code is available at https://github.com/dingmyu/DAPN. Mingyu Ding, Zhiwu Lu 0001, Tao Xiang 0002, Yulei Niu, Jiechao Guan, Ji-Rong Wen	WACV	2
2020	Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow abstract A major challenge for video semantic segmentation is the lack of labeled data. In most benchmark datasets, only one frame of a video clip is annotated, which makes most supervised methods fail to utilize information from the rest of the frames. To exploit the spatio-temporal information in videos, many previous works use pre-computed optical flows, which encode the temporal consistency to improve the video segmentation. However, the video segmentation and optical flow estimation are still considered as two separate tasks. In this paper, we propose a novel framework for joint video semantic segmentation and optical flow estimation. Semantic segmentation brings semantic information to handle occlusion for more robust optical flow estimation, while the non-occluded optical flow provides accurate pixel-level temporal correspondences to guarantee the temporal consistency of the segmentation. Moreover, our framework is able to utilize both labeled and unlabeled frames in the video through joint training, while no additional calculation is required in inference. Extensive experiments show that the proposed model makes the video semantic segmentation and optical flow estimation benefit from each other and outperforms existing methods under the same settings in both tasks. Mingyu Ding, Zhe Wang 0006, Bolei Zhou, Jianping Shi, Zhiwu Lu 0001, Ping Luo 0002	AAAI	1
2020	Learning Depth-Guided Convolutions for Monocular 3D Object Detection abstract 3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information. Conventional 2D convolutions are unsuitable for this task because they fail to capture local object and its scale information, which are vital for 3D object detection. To better represent 3D structure, prior arts typically transform depth maps estimated from 2D images into a pseudo-LiDAR representation, and then apply existing 3D point-cloud based object detectors. However, their results depend heavily on the accuracy of the estimated depth maps, resulting in suboptimal performance. In this work, instead of using pseudo-LiDAR representation, we improve the fundamental 2D fully convolutions by proposing a new local convolutional network (LCN), termed Depth-guided Dynamic-Depthwise-Dilated LCN (D4LCN), where the filters and their receptive fields can be automatically learned from image-based depth maps, making different pixels of different images have different filters. D4LCN overcomes the limitation of conventional 2D convolutions and narrows the gap between image representation and 3D point cloud representation. Extensive experiments show that D4LCN outperforms existing works by large margins. For example, the relative improvement of D4LCN against the state-of-the-art on KITTI is 9.1\% in the moderate setting. D4LCN ranks 1st on KITTI monocular 3D object detection benchmark at the time of submission (car, December 2019). The code is available at https://github.com/dingmyu/D4LCN Mingyu Ding, Yuqi Huo, Hongwei Yi, Zhe Wang 0006, Jianping Shi, Zhiwu Lu 0001, Ping Luo 0002	CVPR	1
2020	Segmenting Transparent Objects in the Wild Enze Xie, Wenjia Wang 0009, Wenhai Wang, Mingyu Ding, Chunhua Shen, Ping Luo 0002	ECCV (13)	4
2020	Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking Jianfeng Yan, Zizhuang Wei, Hongwei Yi, Mingyu Ding, Yisong Chen, Yu-Wing Tai	ECCV (4)	4
2020	Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation Hongwei Yi, Zizhuang Wei, Mingyu Ding, Yisong Chen, Yu-Wing Tai	ECCV (9)	3
2020	SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud abstract 3D vehicle detection based on point cloud is a challenging task in real-world applications such as autonomous driving. Despite significant progress has been made, we observe two aspects to be further improved. First, the semantic context information in LiDAR is seldom explored in previous works, which may help identify ambiguous vehicles. Second, the distribution of point cloud on vehicles varies continuously with increasing depths, which may not be well modeled by a single model. In this work, we propose a unified model SegVoxelNet to address the above two problems. A semantic context encoder is proposed to leverage the free-of-charge semantic segmentation masks in the bird's eye view. Suspicious regions could be highlighted while noisy regions are suppressed by this module. To better deal with vehicles at different depths, a novel depth-aware head is designed to explicitly model the distribution differences and each part of the depth-aware head is made to focus on its own target detection range. Extensive experiments on the KITTI dataset show that the proposed method outperforms the state-of-the-art alternatives in both accuracy and efficiency with point cloud as input only. Hongwei Yi, Shaoshuai Shi, Mingyu Ding, Jiankai Sun, Kui Xu 0004, Hui Zhou 0005, Zhe Wang 0006, Sheng Li 0008	ICRA	3
2019	Face-Focused Cross-Stream Network for Deception Detection in Videos abstract Automated deception detection (ADD) from real-life videos is a challenging task. It specifically needs to address two problems: (1) Both face and body contain useful cues regarding whether a subject is deceptive. How to effectively fuse the two is thus key to the effectiveness of an ADD model. (2) Real-life deceptive samples are hard to collect; learning with limited training data thus challenges most deep learning based ADD models. In this work, both problems are addressed. Specifically, for face-body multimodal learning, a novel face-focused cross-stream network (FFCSN) is proposed. It differs significantly from the popular two-stream networks in that: (a) face detection is added into the spatial stream to capture the facial expressions explicitly, and (b) correlation learning is performed across the spatial and temporal streams for joint deep feature learning across both face and body. To address the training data scarcity problem, our FFCSN model is trained with both meta learning and adversarial learning. Extensive experiments show that our FFCSN model achieves state-of-the-art results. Further, the proposed FFCSN model as well as its robust training strategy are shown to be generally applicable to other human-centric video analysis tasks such as emotion recognition from user-generated videos. Mingyu Ding, Zhiwu Lu 0001, Tao Xiang 0002, Ji-Rong Wen	CVPR	1
2019	CamNet: Coarse-to-Fine Retrieval for Camera Re-Localization abstract Camera re-localization is an important but challenging task in applications like robotics and autonomous driving. Recently, retrieval-based methods have been considered as a promising direction as they can be easily generalized to novel scenes. Despite significant progress has been made, we observe that the performance bottleneck of previous methods actually lies in the retrieval module. These methods use the same features for both retrieval and relative pose regression tasks which have potential conflicts in learning. To this end, here we present a coarse-to-fine retrieval-based deep learning framework, which includes three steps, i.e., image-based coarse retrieval, pose-based fine retrieval and precise relative pose regression. With our carefully designed retrieval module, the relative pose regression task can be surprisingly simpler. We design novel retrieval losses with batch hard sampling criterion and two-stage retrieval to locate samples that adapt to the relative pose regression task. Extensive experiments show that our model (CamNet) outperforms the state-of-the-art methods by a large margin on both indoor and outdoor datasets. Mingyu Ding, Zhe Wang 0006, Jiankai Sun, Jianping Shi, Ping Luo 0002	ICCV	1
2019	Cross-domain mapping learning for transductive zero-shot learning Mingyu Ding, Zhe Wang 0006, Zhiwu Lu 0001	Comput. Vis. Image Underst.	1
2018	DeepInsight: Multi-Task Multi-Scale Deep Learning for Mental Disorder Diagnosis Mingyu Ding, Yuqi Huo, Zhiwu Lu 0001	BMVC	1
2018	Zero-Shot Learning with Superclasses Yuqi Huo, Mingyu Ding, Ji-Rong Wen, Zhiwu Lu 0001	ICONIP (3)	2
2018	InsightGAN: Semi-Supervised Feature Learning with Generative Adversarial Network for Drug Abuse Detection Guangzhen Liu, Mingyu Ding, Yuqi Huo, Zhiwu Lu 0001	ICONIP (3)	4
2018	Domain-Invariant Projection Learning for Zero-Shot Recognition abstract Zero-shot learning (ZSL) aims to recognize unseen object classes without any training samples, which can be regarded as a form of transfer learning from seen classes to unseen ones. This is made possible by learning a projection between a feature space and a semantic space (e.g. attribute space). Key to ZSL is thus to learn a projection function that is robust against the often large domain gap between the seen and unseen classes. In this paper, we propose a novel ZSL model termed domain-invariant projection learning (DIPL). Our model has two novel components: (1) A domain-invariant feature self-reconstruction task is introduced to the seen/unseen class data, resulting in a simple linear formulation that casts ZSL into a min-min optimization problem. Solving the problem is non-trivial, and a novel iterative algorithm is formulated as the solver, with rigorous theoretic algorithm analysis provided. (2) To further align the two domains via the learned projection, shared semantic structure among seen and unseen classes is explored via forming superclasses in the semantic space. Extensive experiments show that our model outperforms the state-of-the-art alternatives by significant margins. Mingyu Ding, Jiechao Guan, Zhiwu Lu 0001, Tao Xiang 0002, Ji-Rong Wen	NeurIPS	2