Yunzhu Li

VLDB 2026 Research / reviewers in the wild / expert

dblp:182/1831 · DBLP profile ↗

← Back

42ranked-venue papers

9as first author

30since 2021 · last 2026

—ORCID · conflict

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

Artificial intelligence and machine learning · 38 · 9 first-author · 27 since 2021Graphics, computer vision, multimedia, augmented reality and games · 11 · 3 first-author · 9 since 2021Systems, architecture and hardware · 7 · 1 first-author · 6 since 2021Applied, interdisciplinary, general and emerging computing · 3 · 2 since 2021

Year	Publication	Venue	Position
2026	Current Agents Fail to Leverage World Model as Tool for Foresight abstract Cheng Qian, Emre Can Acikgoz, Bingxuan Li, Xiusi Chen, Yuji Zhang, Bingxiang He, Qinyu Luo, Gokhan Tur, Dilek Hakkani-Tür, Yunzhu Li, Heng Ji. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026. Cheng Qian 0008, Emre Can Acikgoz, Xiusi Chen, Yuji Zhang 0002, Bingxiang He, Qinyu Luo, Gökhan Tür, Dilek Hakkani-Tür, Yunzhu Li, Heng Ji 0001	ACL (1)	10
2026	Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities abstract State-of-the-art generalist manipulation policies have enabled the deployment of robotic manipulators in unstructured human environments. However, these frameworks struggle in cluttered environments primarily because they utilize auxiliary modules for low-level motion planning and control. Motion planning remains challenging due to the high dimensionality of the robot’s configuration space and the presence of workspace obstacles. Neural motion planners have enhanced motion planning efficiency by offering fast inference and effectively handling the inherent multi-modality of the motion planning problem. Despite such benefits, current neural motion planners often struggle to generalize to unseen, out-of-distribution planning settings. This paper reviews and analyzes the state-of-the-art neural motion planners, highlighting both their benefits and limitations. It also outlines a path toward establishing generalist neural motion planners capable of handling domain-specific challenges. For a list of the reviewed papers, please refer to https://davoodsz.github.io/planning-manip-survey.github.io/. Davood Soleymanzadeh, Ivan Lopez-Sanchez, Hao Su 0002, Yunzhu Li, Xiao Liang 0012, Minghui Zheng	IEEE Trans Autom. Sci. Eng.	4
2025	Learning Structured World Models From and For Physical Interactions abstract Humans have a strong intuitive understanding of the physical world. Through observations and interactions with the environment, we build mental models that predict how the world would change if we applied a specific action (i.e., intuitive physics). My research draws on these human insights to develop model-based RL agents that learn from their interactions and build predictive models that generalize widely across a range of objects made with different materials. The core idea behind my research is to introduce novel representations and integrate structural priors into learning systems to model dynamics at different levels of abstraction. I will discuss how such structures can make model-based planning algorithms more effective, helping robots accomplish complex manipulation tasks (e.g., manipulating an object pile, shaping deformable foam into a target configuration, and making a dumpling from dough using various tools). Yunzhu Li	AAAI	1
2025	EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents abstract Cheng Qian, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Denghui Zhang, Yunzhu Li, Heng Ji. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025. Cheng Qian 0008, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang 0002, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Yunzhu Li, Heng Ji 0001	ACL (1)	11
2025	PhysGen3D: Crafting a Miniature Interactive World from a Single Image abstract Envisioning physically plausible outcomes from a single image requires a deep understanding of the world’s dynamics. To address this, we introduce PhysGen3D, a novel framework that transforms a single image into an amodal, camera-centric, interactive 3D scene. By combining advanced image-based geometric and semantic understanding with physics-based simulation, PhysGen3D creates an interactive 3D world from a static image, enabling us to "imagine" and simulate future scenarios based on user input. At its core, PhysGen3D estimates 3D shapes, poses, physical and lighting properties of objects, thereby capturing essential physical attributes that drive realistic object interactions. This framework allows users to specify precise initial conditions, such as object speed or material properties, for enhanced control over generated video outcomes. We evaluate PhysGen3D’s performance against closed-source state-of-the-art (SOTA) image-to-video models, including Pika, Kling, and Gen-3, showing PhysGen3D’s capacity to generate videos with realistic physics while offering greater flexibility and fine-grained control. Our results show that PhysGen3D achieves a unique balance of photorealism, physical plausibility, and user-driven interactivity, opening new possibilities for generating dynamic, physics-grounded video from an image. Project page: https://by-luckk.github.io/PhysGen3D. Hanxiao Jiang 0001, Saurabh Gupta 0001, Yunzhu Li, Shenlong Wang	CVPR	5
2025	PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos Hanxiao Jiang 0001, Hao-Yu Hsu, Hsin-Ni Yu, Shenlong Wang, Yunzhu Li	ICCV	6
2025	BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics abstract Neural-network-based dynamics models learned from observational data have shown strong predictive capabilities for scene dynamics in robotic manipulation tasks. However, their inherent non-linearity presents significant challenges for effective planning. Current planning methods, often dependent on extensive sampling or local gradient descent, struggle with long-horizon motion planning tasks involving complex contact events. In this paper, we present a GPU-accelerated branch-and-bound (BaB) framework for motion planning in manipulation tasks that require trajectory optimization over neural dynamics models. Our approach employs a specialized branching heuristic to divide the search space into sub-domains and applies a modified bound propagation method, inspired by the state-of-the-art neural network verifier $\alpha,\beta$-CROWN, to efficiently estimate objective bounds within these sub-domains. The branching process guides planning effectively, while the bounding process strategically reduces the search space. Our framework achieves superior planning performance, generating high-quality state-action trajectories and surpassing existing methods in challenging, contact-rich manipulation tasks such as non-prehensile planar pushing with obstacles, object sorting, and rope routing in both simulated and real-world settings. Furthermore, our framework supports various neural network architectures, ranging from simple multilayer perceptrons to advanced graph neural dynamics models, and scales efficiently with different model sizes. Keyi Shen, Jiangwei Yu, Jose A. Barreiros, Yunzhu Li	ICLR	5
2025	Learning Coordinated Bimanual Manipulation Policies Using State Diffusion and Inverse Dynamics Models abstract When performing tasks like laundry, humans naturally coordinate both hands to manipulate objects and anticipate how their actions will change the state of the clothes. However, achieving such coordination in robotics remains challenging due to the need to model object movement, predict future states, and generate precise bimanual actions. In this work, we address these challenges by infusing the predictive nature of human manipulation strategies into robot imitation learning. Specifically, we disentangle task-related state transitions from agent-specific inverse dynamics modeling to enable effective bimanual coordination. Using a demonstration dataset, we train a diffusion model to predict future states given historical observations, envisioning how the scene evolves. Then, we use an inverse dynamics model to compute robot actions that achieve the predicted states. Our key insight is that modeling object movement can help learning policies for bimanual coordination manipulation tasks. Evaluating our framework across diverse simulation and real-world manipulation setups, including multimodal goal configurations, bimanual manipulation, deformable objects, and multi-object setups, we find that it consistently outperforms state-of-the-art state-to-action mapping policies. Our method demonstrates a remarkable capacity to navigate multimodal goal configurations and action distributions, maintain stability across different control modes, and synthesize a broader range of behaviors than those present in the demonstration dataset. Lily Sheng, Tianchen Ji, Shuijing Liu, Yunzhu Li, Katherine Rose Driggs-Campbell	ICRA	6
2025	KUDA: Keypoints to Unify Dynamics Learning and Visual Prompting for Open-Vocabulary Robotic Manipulation abstract With the rapid advancement of large language models (LLMs) and vision-language models (VLMs), significant progress has been made in developing open-vocabulary robotic manipulation systems. However, many existing approaches overlook the importance of object dynamics, limiting their applicability to more complex, dynamic tasks. In this work, we introduce KUDA, an open-vocabulary manipulation system that integrates dynamics learning and visual prompting through keypoints, leveraging both VLMs and learning-based neural dynamics models. Our key insight is that a keypoint-based target specification is simultaneously interpretable by VLMs and can be efficiently translated into cost functions for model-based planning. Given language instructions and visual observations, KUDA first assigns keypoints to the RGB image and queries the VLM to generate target specifications. These abstract keypoint-based representations are then converted into cost functions, which are optimized using a learned dynamics model to produce robotic trajectories. We evaluate KUDA on a range of manipulation tasks, including free-form language instructions across diverse object categories, multi-object interactions, and deformable or granular objects, demonstrating the effectiveness of our framework. The project page is available at http://kuda-dynamics.github.io. Zixian Liu, Mingtong Zhang 0003, Yunzhu Li	ICRA	3
2025	A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards abstract Task specification for robotic manipulation in open-world environments is challenging, requiring flexible and adaptive objectives that align with human intentions and can evolve through iterative feedback. We introduce Iterative Keypoint Reward (IKER), a visually grounded, Python-based reward function that serves as a dynamic task specification. Our framework leverages VLMs to generate and refine these reward functions for multi-step manipulation tasks. Given RGB-D observations and free-form language instructions, we sample keypoints in the scene and generate a reward function conditioned on these keypoints. IKER operates on the spatial relationships between keypoints, leveraging commonsense priors about the desired behaviors, and enabling precise SE(3) control. We reconstruct real-world scenes in simulation and use the generated rewards to train reinforcement learning (RL) policies, which are then deployed into the real world-forming a real-to-sim-to-real loop. Our approach demonstrates notable capabilities across diverse scenarios, including both prehensile and non-prehensile tasks, showcasing multi-step task execution, spontaneous error recovery, and on-the-fly strategy adjustments. The results highlight IKER's effectiveness in enabling robots to perform multi-step tasks in dynamic environments through iterative reward shaping. Project Page: https://iker-robot.github.io/ Shivansh Patel, Xinchen Yin, Wenlong Huang, Shubham Garg, Hooshang Nayyeri, Li Fei-Fei 0001, Svetlana Lazebnik, Yunzhu Li	ICRA	8
2025	Neural Dynamics Augmented Diffusion Policy abstract Imitation learning has been proven effective in mimicking demonstrations across various robotic manipulation tasks. However, to develop robust policies, current imitation methods, such as diffusion policy, require training on extensive demonstrations, making data collection labor-intensive. In contrast, model-based planning with dynamics models can effectively cover a sufficient range of configurations using only off-policy data. Yet, without the guidance of expert demonstrations, many tasks are difficult and time-consuming to plan using the dynamics models. Therefore, we take the best of both model learning and imitation learning, and propose neural dynamics augmented imitation learning that covers a large scene configurations with few-shot demonstrations. This method trains a robust diffusion policy in a local support region using few-shot demonstrations and rearranges objects outside this region into it using offline-trained neural dynamics models. Extensive experiments across various tasks in both simulations and real-world scenarios, including granular manipulation, contact-rich task and multi-object interaction task, have demonstrated that trained with only 1 to 30 demonstrations, our proposed method can robustly cover a significantly larger area than the policy trained purely from the demonstrations. Our project page is available at: https://dynamics-dp.github.io. Ruihai Wu, Mingtong Zhang 0003, Yunzhu Li	ICRA	6
2025	Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper abstract Handheld grippers are increasingly used to collect human demonstrations due to their ease of deployment and versatility. However, most existing designs lack tactile sensing, despite the critical role of tactile feedback in precise manipulation. We present a portable, lightweight gripper with integrated tactile sensors that enables synchronized collection of visual and tactile data in diverse, real-world, and in-the-wild settings. Building on this hardware, we propose a cross-modal representation learning framework that integrates visual and tactile signals while preserving their distinct characteristics. The learning procedure allows the emergence of interpretable representations that consistently focus on contacting regions relevant for physical interactions. When used for downstream manipulation tasks, these representations enable more efficient and effective policy learning, supporting precise robotic manipulation based on multimodal feedback. We validate our approach on fine-grained tasks such as test tube insertion and pipette-based fluid transfer, demonstrating improved accuracy and robustness under external disturbances. Our project page is available at \url{https://binghao-huang.github.io/touch_in_the_wild/}. Xinyue Zhu, Binghao Huang, Yunzhu Li	NeurIPS	3
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.	4
2024	Partial-View Object View Synthesis via Filtering Inversion abstract We propose Filtering Inversion (FINV), a learning framework and optimization process that predicts a renderable 3D object representation from one or few partial views. FINV addresses the challenge of synthesizing novel views of objects from partial observations, spanning cases where the object is not entirely in view, is partially occluded, or is only observed from similar views. To achieve this, FINV learns shape priors by training a 3D generative model. At inference, given one or more views of a novel real-world object, FINV first finds a set of latent codes for the object by inverting the generative model from multiple initial seeds. Maintaining the set of latent codes, FINV filters and resamples them after receiving each new observation, akin to particle filtering. The generator is then finetuned for each latent code on the available views in order to adapt to novel objects. We show that FINV successfully synthesizes novel views of real-world objects (e.g., chairs, tables, and cars), even if the generative prior is trained only on synthetic objects. The ability to address the sim-to-real problem allows FINV to be used for object categories without real-world datasets. FINV achieves state-of-the-art performance on multiple real-world datasets, recovers object shape and texture from partial and sparse views, is robust to occlusion, and is able to incrementally improves its representation with more observations. Fan-Yun Sun, Jonathan Tremblay, Valts Blukis, Danfei Xu, Boris Ivanovic, Péter Karkus, Stanley T. Birchfield, Dieter Fox, Yunzhu Li, Jiajun Wu 0001, Marco Pavone 0001, Nick Haber	3DV	11
2024	BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation abstract The systematic evaluation and understanding of computer vision models under varying conditions require large amounts of data with comprehensive and customized labels, which real-world vision datasets rarely satisfy. While current synthetic data generators offer a promising alternative, particularly for embodied AI tasks, they often fall short for computer vision tasks due to low asset and rendering quality, limited diversity, and unrealistic physical properties. We introduce the BEHAVIOR Vision Suite (BVS), a set of tools and assets to generate fully customized synthetic data for systematic evaluation of computer vision models, based on the newly developed embodied AI benchmark, BEHAVIOR-1 K. BVS supports a large number of adjustable parameters at the scene level (e.g., lighting, object placement), the object level (e.g., joint configuration, attributes such as “filled” and “folded”), and the camera level (e.g., field of view, focal length). Researchers can arbitrarily vary these parameters during data generation to perform controlled experiments. We showcase three example application scenarios: systematically evaluating the robustness of models across different continuous axes of domain shift, evaluating scene understanding models on the same set of images, and training and evaluating simulation-to-real transfer for a novel vision task: unary and binary state prediction. Project website: https://behavior-vision-suite.github.io/ Yunhao Ge, Yihe Tang, Cem Gökmen, Chengshu Li 0001, Wensi Ai, Benjamin Jose Martinez, Arman Aydin, Mona Anvari, Ayush K. Chakravarthy, Hong-Xing Yu, Josiah Wong, Sanjana Srivastava, Sharon Lee, Shengxin Zha, Laurent Itti, Yunzhu Li, Roberto Martin Martin, Miao Liu 0007, Pengchuan Zhang, Li Fei-Fei 0001, Jiajun Wu 0001	CVPR	17
2024	Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians Licheng Zhong, Hong-Xing Yu, Jiajun Wu 0001, Yunzhu Li	ECCV (2)	4
2024	Executable Code Actions Elicit Better LLM Agents abstract Large Language Model (LLM) agents, capable of performing a broad range of actions, such as invoking tools and controlling robots, show great potential in tackling real-world challenges. LLM agents are typically prompted to produce actions by generating JSON or text in a pre-defined format, which is usually limited by constrained action space (e.g., the scope of pre-defined tools) and restricted flexibility (e.g., inability to compose multiple tools). This work proposes to use executable Python code to consolidate LLM agents’ actions into a unified action space (CodeAct). Integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations through multi-turn interactions. Our extensive analysis of 17 LLMs on API-Bank and a newly curated benchmark shows that CodeAct outperforms widely used alternatives (up to 20% higher success rate). The encouraging performance of CodeAct motivates us to build an open-source LLM agent that interacts with environments by executing interpretable code and collaborates with users using natural language. To this end, we collect an instruction-tuning dataset CodeActInstruct that consists of 7k multi-turn interactions using CodeAct. We show that it can be used with existing data to improve models in agent-oriented tasks without compromising their general capability. CodeActAgent, finetuned from Llama2 and Mistral, is integrated with Python interpreter and uniquely tailored to perform sophisticated tasks (e.g., model training) using existing libraries and autonomously self-debug. Xingyao Wang 0002, Yangyi Chen, Lifan Yuan, Yizhe Zhang 0002, Yunzhu Li, Hao Peng 0009, Heng Ji 0001	ICML	5
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	272
2023	The Object Folder Benchmark : Multisensory Learning with Neural and Real Objects abstract We introduce the ObjectFolder Benchmark, a benchmark suite of 10 tasks for multisensory object-centric learning, centered around object recognition, reconstruction, and manipulation with sight, sound, and touch. We also introduce the Objectfolder Real dataset, including the multisensory measurements for 100 real-world household objects, building upon a newly designed pipeline for collecting the 3D meshes, videos, impact sounds, and tactile readings of real-world objects. We conduct systematic benchmarking on both the 1,000 multisensory neural objects from Objectfolder, and the real multisensory data from Objectfolder Real. Our results demonstrate the importance of multisensory perception and reveal the respective roles of vision, audio, and touch for different object-centric learning tasks. By publicly releasing our dataset and benchmark suite, we hope to catalyze and enable new research in multisensory object-centric learning in computer vision, robotics, and beyond. Project page: https://objectfolder.stanford.edu Ruohan Gao, Yiming Dou, Hao Li 0076, Tanmay Agarwal, Jeannette Bohg, Yunzhu Li, Li Fei-Fei 0001, Jiajun Wu 0001	CVPR	6
2023	Multi-Object Manipulation via Object-Centric Neural Scattering Functions abstract Learned visual dynamics models have proven effective for robotic manipulation tasks. Yet, it remains unclear how best to represent scenes involving multi-object interactions. Current methods decompose a scene into discrete objects, but they struggle with precise modeling and manipulation amid challenging lighting conditions as they only encode appearance tied with specific illuminations. In this work, we propose using object-centric neural scattering functions (OSFs) as object representations in a model-predictive control framework. OSFs model per-object light transport, enabling compositional scene re-rendering under object rearrangement and varying lighting conditions. By combining this approach with inverse parameter estimation and graph-based neural dynamics models, we demonstrate improved model-predictive control performance and generalization in compositional multi-object environments, even in previously unseen scenarios and harsh lighting conditions. Stephen Tian, Yancheng Cai, Hong-Xing Yu, Sergey Zakharov, Katherine Liu, Adrien Gaidon, Yunzhu Li, Jiajun Wu 0001	CVPR	7
2023	Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision? Lirui Wang, Kaiqing Zhang, Yunzhu Li, Yonglong Tian, Russ Tedrake	ICLR	3
2023	Model-Based Control with Sparse Neural Dynamics abstract Learning predictive models from observations using deep neural networks (DNNs) is a promising new approach to many real-world planning and control problems. However, common DNNs are too unstructured for effective planning, and current control methods typically rely on extensive sampling or local gradient descent. In this paper, we propose a new framework for integrated model learning and predictive control that is amenable to efficient optimization algorithms. Specifically, we start with a ReLU neural model of the system dynamics and, with minimal losses in prediction accuracy, we gradually sparsify it by removing redundant neurons. This discrete sparsification process is approximated as a continuous problem, enabling an end-to-end optimization of both the model architecture and the weight parameters. The sparsified model is subsequently used by a mixed-integer predictive controller, which represents the neuron activations as binary variables and employs efficient branch-and-bound algorithms. Our framework is applicable to a wide variety of DNNs, from simple multilayer perceptrons to complex graph neural dynamics. It can efficiently handle tasks involving complicated contact dynamics, such as object pushing, compositional object sorting, and manipulation of deformable objects. Numerical and hardware experiments show that, despite the aggressive sparsification, our framework can deliver better closed-loop performance than existing state-of-the-art methods. Ziang Liu 0008, Genggeng Zhou, Jeff He, Tobia Marcucci, Li Fei-Fei 0001, Jiajun Wu 0001, Yunzhu Li	NeurIPS	7
2023	3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes abstract Given a visual scene, humans have strong intuitions about how a scene can evolve over time under given actions. The intuition, often termed visual intuitive physics, is a critical ability that allows us to make effective plans to manipulate the scene to achieve desired outcomes without relying on extensive trial and error. In this paper, we present a framework capable of learning 3D-grounded visual intuitive physics models from videos of complex scenes with fluids. Our method is composed of a conditional Neural Radiance Field (NeRF)-style visual frontend and a 3D point-based dynamics prediction backend, using which we can impose strong relational and structural inductive bias to capture the structure of the underlying environment. Unlike existing intuitive point-based dynamics works that rely on the supervision of dense point trajectory from simulators, we relax the requirements and only assume access to multi-view RGB images and (imperfect) instance masks acquired using color prior. This enables the proposed model to handle scenarios where accurate point estimation and tracking are hard or impossible. We generate datasets including three challenging scenarios involving fluid, granular materials, and rigid objects in the simulation. The datasets do not include any dense particle information so most previous 3D-based intuitive physics pipelines can barely deal with that. We show our model can make long-horizon future predictions by learning from raw images and significantly outperforms models that do not employ an explicit 3D representation space. We also show that once trained, our model can achieve strong generalization in complex scenarios under extrapolate settings. Antonio Torralba 0001, Josh Tenenbaum, Dan Yamins, Yunzhu Li, Hsiao-Yu Fish Tung	NeurIPS	5
2023	Algorithms and Systems for Manipulating Multiple Objects abstract Robot manipulation of multiple objects is an important topic for applications including warehouse automation, service robots performing cleaning, and large-scale object sorting. Although problems can range in complexity from a few objects to large disordered piles, autonomy remains a significant technical challenge due to the high-dimensional joint configuration space of the robot and all objects, the complex dynamics of object interaction, and the ambiguity and occlusion caused by clutter. This article surveys a broad range of classical and state-of-the-art research in multiobject manipulation and categorizes them along the dimensions of tasks, perception, predictive models, and decision-making algorithms. It also covers emerging trends and open problems faced in the ongoing effort to realize robust multiobject manipulation systems in practice. Zherong Pan, Andy Zeng 0001, Yunzhu Li, Jingjin Yu, Kris Hauser	IEEE Trans. Robotics	3
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	3
2022	DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools Zhiao Huang, Yunzhu Li, Josh Tenenbaum, David Held, Chuang Gan 0001	ICLR	3
2022	ActionSense: A Multimodal Dataset and Recording Framework for Human Activities Using Wearable Sensors in a Kitchen Environment abstract This paper introduces ActionSense, a multimodal dataset and recording framework with an emphasis on wearable sensing in a kitchen environment. It provides rich, synchronized data streams along with ground truth data to facilitate learning pipelines that could extract insights about how humans interact with the physical world during activities of daily living, and help lead to more capable and collaborative robot assistants. The wearable sensing suite captures motion, force, and attention information; it includes eye tracking with a first-person camera, forearm muscle activity sensors, a body-tracking system using 17 inertial sensors, finger-tracking gloves, and custom tactile sensors on the hands that use a matrix of conductive threads. This is coupled with activity labels and with externally-captured data from multiple RGB cameras, a depth camera, and microphones. The specific tasks recorded in ActionSense are designed to highlight lower-level physical skills and higher-level scene reasoning or action planning. They include simple object manipulations (e.g., stacking plates), dexterous actions (e.g., peeling or cutting vegetables), and complex action sequences (e.g., setting a table or loading a dishwasher). The resulting dataset and underlying experiment framework are available at https://action-sense.csail.mit.edu. Preliminary networks and analyses explore modality subsets and cross-modal correlations. ActionSense aims to support applications including learning from demonstrations, dexterous robot control, cross-modal predictions, and fine-grained action segmentation. It could also help inform the next generation of smart textiles that may one day unobtrusively send rich data streams to in-home collaborative or autonomous robot assistants. Joseph DelPreto, Chao Liu 0021, Yiyue Luo, Michael Foshey, Yunzhu Li, Antonio Torralba 0001, Wojciech Matusik, Daniela Rus	NeurIPS	5
2022	Reinforcement Learning with Neural Radiance Fields abstract It is a long-standing problem to find effective representations for training reinforcement learning (RL) agents. This paper demonstrates that learning state representations with supervision from Neural Radiance Fields (NeRFs) can improve the performance of RL compared to other learned representations or even low-dimensional, hand-engineered state information. Specifically, we propose to train an encoder that maps multiple image observations to a latent space describing the objects in the scene. The decoder built from a latent-conditioned NeRF serves as the supervision signal to learn the latent space. An RL algorithm then operates on the learned latent space as its state representation. We call this NeRF-RL. Our experiments indicate that NeRF as supervision leads to a latent space better suited for the downstream RL tasks involving robotic object manipulations like hanging mugs on hooks, pushing objects, or opening doors.Video: https://dannydriess.github.io/nerf-rl Danny Drieß, Ingmar Schubert, Peter R. Florence, Yunzhu Li, Marc Toussaint	NeurIPS	4
2021	Intelligent Carpet: Inferring 3D Human Pose From Tactile Signals abstract Daily human activities, e.g., locomotion, exercises, and resting, are heavily guided by the tactile interactions between the human and the ground. In this work, leveraging such tactile interactions, we propose a 3D human pose estimation approach using the pressure maps recorded by a tactile carpet as input. We build a low-cost, high-density, large-scale intelligent carpet, which enables the real-time recordings of human-floor tactile interactions in a seamless manner. We collect a synchronized tactile and visual dataset on various human activities. Employing a state-of-the-art camera-based pose estimation model as supervision, we design and implement a deep neural network model to infer 3D human poses using only the tactile information. Our pipeline can be further scaled up to multi-person pose estimation. We evaluate our system and demonstrate its potential applications in diverse fields. Yiyue Luo, Yunzhu Li, Michael Foshey, Wan Shou, Pratyusha Sharma, Tomás Palacios, Antonio Torralba 0001, Wojciech Matusik	CVPR	2
2021	Dynamic Modeling of Hand-Object Interactions via Tactile Sensing abstract Tactile sensing is critical for humans to perform everyday tasks. While significant progress has been made in analyzing object grasping from vision, it remains unclear how we can utilize tactile sensing to reason about and model the dynamics of hand-object interactions. In this work, we employ a high-resolution tactile glove to perform four different interactive activities on a diversified set of objects. We propose a framework aiming at predicting the 3d locations of both the hand and the object purely from the touch data by combining a predictive model and a contrastive learning module. This framework can reason about the interaction patterns from the tactile data, hallucinate the changes in the environment, esti-mate the uncertainty of the prediction, and generalize to unseen objects. We also provide detailed ablation studies regarding different system designs as well as visualizations of the predicted trajectories. This work takes a step on dynamics modeling in hand-object interactions from dense tactile sensing, which opens the door for future applications in activity learning, human-computer interactions, and imitation learning for robotics. Yunzhu Li, Yiyue Luo, Wan Shou, Michael Foshey, Junchi Yan, Josh Tenenbaum, Wojciech Matusik, Antonio Torralba 0001	IROS	2
2020	Learning Compositional Koopman Operators for Model-Based Control Yunzhu Li, Hao He 0011, Jiajun Wu 0001, Dina Katabi, Antonio Torralba 0001	ICLR	1
2020	CLEVRER: Collision Events for Video Representation and Reasoning Kexin Yi, Chuang Gan 0001, Yunzhu Li, Pushmeet Kohli, Jiajun Wu 0001, Antonio Torralba 0001, Josh Tenenbaum	ICLR	3
2020	Visual Grounding of Learned Physical Models abstract Humans intuitively recognize objects’ physical properties and predict their motion, even when the objects are engaged in complicated interactions. The abilities to perform physical reasoning and to adapt to new environments, while intrinsic to humans, remain challenging to state-of-the-art computational models. In this work, we present a neural model that simultaneously reasons about physics and makes future predictions based on visual and dynamics priors. The visual prior predicts a particle-based representation of the system from visual observations. An inference module operates on those particles, predicting and refining estimates of particle locations, object states, and physical parameters, subject to the constraints imposed by the dynamics prior, which we refer to as visual grounding. We demonstrate the effectiveness of our method in environments involving rigid objects, deformable materials, and fluids. Experiments show that our model can infer the physical properties within a few observations, which allows the model to quickly adapt to unseen scenarios and make accurate predictions into the future. Yunzhu Li, Toru Lin, Kexin Yi, Daniel Bear, Dan Yamins, Jiajun Wu 0001, Josh Tenenbaum, Antonio Torralba 0001	ICML	1
2020	Two-stage and dual-decoder convolutional U-Net ensembles for reliable vessel and plaque segmentation in carotid ultrasound images abstract Carotid ultrasound is a screening modality used by physicians to direct treatment in the prevention of ischemic stroke in high-risk patients. It is a time intensive process that requires highly trained technicians and physicians. Evaluation of a carotid ultrasound requires segmentation of the vessel wall, lumen, and plaque of the carotid artery. Convolutional neural networks are state of the art in image segmentation yet there are no previous methods to solve this problem on carotid ultrasounds. We introduce two novel convolutional U-net models for both vessel and plaque from ultrasound images of the entire carotid system. We obtained de-identified images under IRB approval from 226 patients. We isolated a total of 500 ultrasound images spanning the internal, external, and common carotid arteries. We manually segmented the vessel lumen and plaque in each image that we then use as ground truth. In 10-fold cross-validation all models attain over 90% accuracy for vessel segmentation. With a basic convolutional U-Net we obtained an accuracy of 66.8% for plaque segmentation. With our dual-decoder model we see an improvement to 68.8% whereas our two-stage model falls behind at 65.1% accuracy. However, if we gave our two-stage model the true correct vessel as input its plaque accuracy rises to 81.7% suggesting that the method has potential and needs more work. We ensemble our U-Net and dual decoder U-Net models to obtain confidence scores for segmentations. By considering high confidence outputs above the 60% and 80% thresholds the accuracy of our dual decoder U-Net rises to 75.2% and 87.3% respectively. Our work here shows the potential of dual and two-stage methods for vessel and plaque segmentation in carotid artery ultrasound images and is an important first step in creating a system that can independently evaluate carotid ultrasounds. Meiyan Xie, Yunzhu Li, Yunzhe Xue, Lauren Huntress, William Beckerman, Saum A. Rahimi, Justin W. Ady, Usman Roshan	ICMLA	2
2020	Learning Physical Graph Representations from Visual Scenes abstract Convolutional Neural Networks (CNNs) have proved exceptional at learning representations for visual object categorization. However, CNNs do not explicitly encode objects, parts, and their physical properties, which has limited CNNs' success on tasks that require structured understanding of visual scenes. To overcome these limitations, we introduce the idea of ``Physical Scene Graphs'' (PSGs), which represent scenes as hierarchical graphs, with nodes in the hierarchy corresponding intuitively to object parts at different scales, and edges to physical connections between parts. Bound to each node is a vector of latent attributes that intuitively represent object properties such as surface shape and texture. We also describe PSGNet, a network architecture that learns to extract PSGs by reconstructing scenes through a PSG-structured bottleneck. PSGNet augments standard CNNs by including: recurrent feedback connections to combine low and high-level image information; graph pooling and vectorization operations that convert spatially-uniform feature maps into object-centric graph structures; and perceptual grouping principles to encourage the identification of meaningful scene elements. We show that PSGNet outperforms alternative self-supervised scene representation algorithms at scene segmentation tasks, especially on complex real-world images, and generalizes well to unseen object types and scene arrangements. PSGNet is also able learn from physical motion, enhancing scene estimates even for static images. We present a series of ablation studies illustrating the importance of each component of the PSGNet architecture, analyses showing that learned latent attributes capture intuitive scene properties, and illustrate the use of PSGs for compositional scene inference. Daniel Bear, Chaofei Fan, Damian Mrowca, Yunzhu Li, Seth Alter, Aran Nayebi, Jeremy Schwartz, Li Fei-Fei 0001, Jiajun Wu 0001, Josh Tenenbaum, Dan Yamins	NeurIPS	4
2020	Causal Discovery in Physical Systems from Videos abstract Causal discovery is at the core of human cognition. It enables us to reason about the environment and make counterfactual predictions about unseen scenarios that can vastly differ from our previous experiences. We consider the task of causal discovery from videos in an end-to-end fashion without supervision on the ground-truth graph structure. In particular, our goal is to discover the structural dependencies among environmental and object variables: inferring the type and strength of interactions that have a causal effect on the behavior of the dynamical system. Our model consists of (a) a perception module that extracts a semantically meaningful and temporally consistent keypoint representation from images, (b) an inference module for determining the graph distribution induced by the detected keypoints, and (c) a dynamics module that can predict the future by conditioning on the inferred graph. We assume access to different configurations and environmental conditions, i.e., data from unknown interventions on the underlying system; thus, we can hope to discover the correct underlying causal graph without explicit interventions. We evaluate our method in a planar multi-body interaction environment and scenarios involving fabrics of different shapes like shirts and pants. Experiments demonstrate that our model can correctly identify the interactions from a short sequence of images and make long-term future predictions. The causal structure assumed by the model also allows it to make counterfactual predictions and extrapolate to systems of unseen interaction graphs or graphs of various sizes. Yunzhu Li, Antonio Torralba 0001, Anima Anandkumar, Dieter Fox, Animesh Garg	NeurIPS	1
2019	Vessel lumen segmentation in internal carotid artery ultrasounds with deep convolutional neural networks abstract Carotid ultrasound is a screening modality used by physicians to direct treatment in the prevention of ischemic stroke in high-risk patients. It is a time intensive process that requires highly trained technicians and physicians. Evaluation of a carotid ultrasound requires identification of the vessel wall, lumen, and plaque of the carotid artery. Automated machine learning methods for these tasks are highly limited. We propose and evaluate here single and multi-path convolutional U-neural network for lumen identification from ultrasound images. We obtained de-identified images under IRB approval from 98 patients. We isolated just the internal carotid artery ultrasound images for these patients giving us a total of 302 images. We manually segmented the vessel lumen, which we use as ground truth to develop and validate our model. With a basic simple convolutional U-Net we obtained a 10-fold cross-validation accuracy of 95%. We also evaluated a dual-path U-Net where we modified the original image and used it as a synthetic modality but we found no improvement in accuracy. We found that the sample size made a considerable difference and thus expect our accuracy to rise as we add more training samples to the model. Our work here represents a first successful step towards the automated identification of the vessel lumen in carotid artery ultrasound images and is an important first step in creating a system that can independently evaluate carotid ultrasounds. Meiyan Xie, Yunzhu Li, Yunzhe Xue, Randy Shafritz, Saum A. Rahimi, Justin W. Ady, Usman Roshan	BIBM	2
2019	Connecting Touch and Vision via Cross-Modal Prediction abstract Humans perceive the world using multi-modal sensory inputs such as vision, audition, and touch. In this work, we investigate the cross-modal connection between vision and touch. The main challenge in this cross-domain modeling task lies in the significant scale discrepancy between the two: while our eyes perceive an entire visual scene at once, humans can only feel a small region of an object at any given moment. To connect vision and touch, we introduce new tasks of synthesizing plausible tactile signals from visual inputs as well as imagining how we interact with objects given tactile data as input. To accomplish our goals, we first equip robots with both visual and tactile sensors and collect a large-scale dataset of corresponding vision and tactile image sequences. To close the scale gap, we present a new conditional adversarial model that incorporates the scale and location information of the touch. Human perceptual studies demonstrate that our model can produce realistic visual images from tactile data and vice versa. Finally, we present both qualitative and quantitative experimental results regarding different system designs, as well as visualizing the learned representations of our model. Yunzhu Li, Jun-Yan Zhu, Russ Tedrake, Antonio Torralba 0001	CVPR	1
2019	Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids Yunzhu Li, Jiajun Wu 0001, Russ Tedrake, Josh Tenenbaum, Antonio Torralba 0001	ICLR (Poster)	1
2019	Propagation Networks for Model-Based Control Under Partial Observation abstract There has been an increasing interest in learning dynamics simulators for model-based control. Compared with off-the-shelf physics engines, a learnable simulator can quickly adapt to unseen objects, scenes, and tasks. However, existing models like interaction networks only work for fully observable systems; they also only consider pairwise interactions within a single time step, both restricting their use in practical systems. We introduce Propagation Networks (PropNet), a differentiable, learnable dynamics model that handles partially observable scenarios and enables instantaneous propagation of signals beyond pairwise interactions. With these innovations, our propagation networks not only outperform current learnable physics engines in forward simulation, but also achieves superior performance on various control tasks. Compared with existing deep reinforcement learning algorithms, model-based control with propagation networks is more accurate, efficient, and generalizable to novel, partially observable scenes and tasks. Yunzhu Li, Jiajun Wu 0001, Jun-Yan Zhu, Josh Tenenbaum, Antonio Torralba 0001, Russ Tedrake	ICRA	1
2017	InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations abstract The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are typically not explicitly modeled. In this paper, we propose a new algorithm that can infer the latent structure of expert demonstrations in an unsupervised way. Our method, built on top of Generative Adversarial Imitation Learning, can not only imitate complex behaviors, but also learn interpretable and meaningful representations of complex behavioral data, including visual demonstrations. In the driving domain, we show that a model learned from human demonstrations is able to both accurately reproduce a variety of behaviors and accurately anticipate human actions using raw visual inputs. Compared with various baselines, our method can better capture the latent structure underlying expert demonstrations, often recovering semantically meaningful factors of variation in the data. Yunzhu Li, Jiaming Song, Stefano Ermon	NIPS	1
2016	Face Detection with End-to-End Integration of a ConvNet and a 3D Model Yunzhu Li, Benyuan Sun, Tianfu Wu 0001, Yizhou Wang 0001	ECCV (3)	1