Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks. However, a major challenge in developing generalized GUI agents is the lack of sufficient trajectory data across various operating systems and applications, mainly due to the high cost of manual annotations. In this paper, we propose the TongUI framework that transforms millions of multimodal web tutorials into GUI trajectories for generalized GUI agents. Concretely, we crawl GUI videos and articles from the Internet and process them into GUI agent trajectory data. Based on this, we construct the GUI-Net-1M dataset, which contains 1 million trajectories across five operating systems and over 280 applications. To the best of our knowledge, this is the largest open-source GUI trajectory dataset. We develop the TongUI agent by fine-tuning Qwen2.5-VL-3B/7B/32B models on GUI-Net-1M, which shows consistent performance improvements on commonly used grounding and navigation benchmarks, outperforming baseline agents by 10\% on multiple benchmarks, showing the effectiveness of the GUI-Net-1M dataset and underscoring the significance of our TongUI framework.

Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neural rendering methods as 3D representations and jointly optimize color and semantic features to achieve rendering and scene understanding simultaneously. In this paper, we introduce Semantic Gaussians, a novel open-vocabulary scene understanding approach based on 3D Gaussian Splatting. Our key idea is to distill knowledge from 2D pretrained models to 3D Gaussians. Unlike existing methods, we design a versatile projection approach that maps various 2D semantic features from pre-trained image encoders into a novel semantic component of 3D Gaussians, which is based on spatial relationships and needs no additional training. We further build a 3D semantic network that directly predicts the semantic component from raw 3D Gaussians for fast inference. The quantitative results on ScanNet segmentation and LERF object localization demonstrate the superior performance of our method. Additionally, we explore several applications of Semantic Gaussians, including object part segmentation, instance segmentation, scene editing, and spatiotemporal segmentation, with better qualitative results over 2D and 3D baselines, highlighting its versatility and effectiveness in supporting diverse downstream tasks.

Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is bridging the gap between discrete entities in low-level observations and the abstract concepts required for effective planning. A common solution is building hierarchical agents, where VLMs serve as high-level reasoners that break down tasks into executable sub-tasks, typically specified using language. However, language suffers from the inability to communicate detailed spatial information. We propose visual-temporal context prompting, a novel communication protocol between VLMs and policy models. This protocol leverages object segmentation from past observations to guide policy-environment interactions. Using this approach, we train ROCKET-1, a low-level policy that predicts actions based on concatenated visual observations and segmentation masks, supported by real-time object tracking from SAM-2. Our method unlocks the potential of VLMs, enabling them to tackle complex tasks that demand spatial reasoning. Experiments in Minecraft show that our approach enables agents to achieve previously unattainable tasks, with a 76% absolute improvement in open-world interaction performance. Codes are available at https://craftjarvis.github.io/ROCKET-1.

Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus on grounding objects in static observations from 3D reconstruction, such as meshes and point clouds, but lack the ability to actively perceive and explore their environment. To address this limitation, we introduce \underline{\textbf{M}}ove \underline{\textbf{t}}o \underline{\textbf{U}}nderstand (\textbf{\model}), a unified framework that integrates active perception with \underline{\textbf{3D}} vision-language learning, enabling embodied agents to effectively explore and understand their environment. This is achieved by three key innovations: 1) Online query-based representation learning, enabling direct spatial memory construction from RGB-D frames, eliminating the need for explicit 3D reconstruction. 2) A unified objective for grounding and exploring, which represents unexplored locations as frontier queries and jointly optimizes object grounding and frontier selection. 3) End-to-end trajectory learning that combines \textbf{V}ision-\textbf{L}anguage-\textbf{E}xploration pre-training over a million diverse trajectories collected from both simulated and real-world RGB-D sequences. Extensive evaluations across various embodied navigation and question-answering benchmarks show that MTU3D outperforms state-of-the-art reinforcement learning and modular navigation approaches by 14\%, 23\%, 9\%, and 2\% in success rate on HM3D-OVON, GOAT-Bench, SG3D, and A-EQA, respectively. \model's versatility enables navigation using diverse input modalities, including categories, language descriptions, and reference images. These findings highlight the importance of bridging visual grounding and exploration for embodied intelligence.

Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI. Although large-scale pre-training on unlabeled datasets has enabled agents to learn diverse behaviors, these agents often struggle with following instructions. While augmenting the dataset with instruction labels can mitigate this issue, acquiring such high-quality annotations at scale is impractical. To address this issue, we frame the problem as a semi-supervised learning task and introduce \agent, a multimodal instructable agent trained using a novel approach that combines weak supervision with latent variable models. Our method consists of two key components: constrained self-imitating, which utilizes large amounts of unlabeled demonstrations to enable the policy to learn diverse behaviors, and human intention alignment, which uses a smaller set of labeled demonstrations to ensure the latent space reflects human intentions. \agent’s effectiveness is validated across four diverse environments, ranging from video games to robotic manipulation, demonstrating its robust multimodal instruction-following capabilities.

The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal agent tuning method that automatically generates multi-modal tool-usage data and tunes a vision-language model (VLM) as the controller for powerful tool-usage reasoning. To preserve the data quality, we prompt the GPT-4o mini model to generate queries, files, and trajectories, followed by query-file and trajectory verifiers. Based on the data synthesis pipeline, we collect the MM-Traj dataset that contains 20K tasks with trajectories of tool usage. Then, we develop the T3-Agent via Trajectory Tuning on VLMs for Tool usage using MM-Traj. Evaluations on the GTA and GAIA benchmarks show that the T3-Agent consistently achieves improvements on two popular VLMs: MiniCPM-V-8.5B and Qwen2-VL-7B, which outperforms untrained VLMs by 20%, showing the effectiveness of the proposed data synthesis pipeline, leading to high-quality data for tool-usage capabilities.

Diffusion policies are widely adopted in complex visuomotor tasks for their ability to capture multimodal action distributions. However, the multiple sampling steps required for action generation significantly harm real-time inference efficiency, which limits their applicability in real-time decision-making scenarios. Existing acceleration techniques either require retraining or degrade performance under low sampling steps. Here we propose Falcon, which mitigates this speed-performance trade-off and achieves further acceleration. The core insight is that visuomotor tasks exhibit sequential dependencies between actions. Falcon leverages this by reusing partially denoised actions from historical information rather than sampling from Gaussian noise at each step. By integrating current observations, Falcon reduces sampling steps while preserving performance. Importantly, Falcon is a training-free algorithm that can be applied as a plug-in to further improve decision efficiency on top of existing acceleration techniques. We validated Falcon in 48 simulated environments and 2 real-world robot experiments. demonstrating a 2-7x speedup with negligible performance degradation, offering a promising direction for efficient visuomotor policy design.

Multimodal agents, which integrate a controller (e.g., a vision language model) with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks. Existing approaches for training these agents, both supervised fine-tuning and reinforcement learning, depend on extensive human-annotated task-answer pairs and tool trajectories. However, for complex multimodal tasks, such annotations are prohibitively expensive or impractical to obtain. In this paper, we propose an iterative tool usage exploration method for multimodal agents without any pre-collected data, namely SPORT, via step-wise preference optimization to refine the trajectories of tool usage. Our method enables multimodal agents to autonomously discover effective tool usage strategies through self-exploration and optimization, eliminating the bottleneck of human annotation. SPORT has four iterative components: task synthesis, step sampling, step verification, and preference tuning. We first synthesize multimodal tasks using language models. Then, we introduce a novel trajectory exploration scheme, where step sampling and step verification are executed alternately to solve synthesized tasks. In step sampling, the agent tries different tools and obtains corresponding results. In step verification, we employ a verifier to provide AI feedback to construct step-wise preference data. The data is subsequently used to update the controller for tool usage through preference tuning, producing a SPORT agent. By interacting with real environments, the SPORT agent gradually evolves into a more refined and capable system. Evaluation in the GTA and GAIA benchmarks shows that the SPORT agent achieves 6.41% and 3.64% improvements, underscoring the generalization and effectiveness introduced by our method.

3D visual grounding has made notable progress in localizing objects within complex 3D scenes. However, grounding referring expressions beyond objects in 3D scenes remains unexplored. In this paper, we introduce Anywhere3D-Bench, a holistic 3D visual grounding benchmark consisting of 2,886 referring expression-3D bounding box pairs spanning four different grounding levels: human-activity areas, unoccupied space beyond objects, individual objects in the scene, and fine-grained object parts. We assess a range of state-of-the-art 3D visual grounding methods alongside large language models (LLMs) and multimodal LLMs (MLLMs) on Anywhere3D-Bench. Experimental results reveal that space-level and part-level visual grounding pose the greatest challenges: space-level tasks require a more comprehensive spatial reasoning ability, for example, modeling distances and spatial relations within 3D space, while part-level tasks demand fine-grained perception of object composition. Even the best performance model, OpenAI o4-mini, achieves only 23.00% accuracy on space-level tasks and 31.46% on part-level tasks, significantly lower than its performance on area-level and object-level tasks. These findings underscore a critical gap in current models’ capacity to understand and reason about 3D scenes beyond object-level semantics.

Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approaches generate the entire target image rather than selectively regenerate only the intended editing areas. This results in (1) unnecessary computational costs and (2) a bias toward reconstructing non-editing regions, which compromises the quality of the intended edits. To resolve these limitations, we propose to formulate image editing as $\textbf{N}$ext $\textbf{E}$diting-token $\textbf{P}$rediction (NEP) based on autoregressive image generation, where only regions that need to be edited are regenerated, thus avoiding unintended modification to the non-editing areas. To enable any-region editing, we propose to pre-train an any-order autoregressive text-to-image (T2I) model. Once trained, it is capable of zero-shot image editing and can be easily adapted to NEP for image editing, which achieves a new state-of-the-art on widely used image editing benchmarks. Moreover, our model naturally supports test-time scaling (TTS) through iteratively refining its generation in a zero-shot manner.

Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle when the number of open-world tasks could potentially be infinite and lack the capability to progressively enhance task completion as game time progresses. We introduceJARVIS-1, an open-world agent that can perceive multimodal input (visual observations and human instructions), generate sophisticated plans, and perform embodied control, all within the popular yet challenging open-world Minecraft universe. Specifically, we developJARVIS-1 on top of pre-trained multimodal language models, which map visual observations and textual instructions to plans. The plans will be ultimately dispatched to the goal-conditioned controllers. We outfitJARVIS-1 with a multimodal memory, which facilitates planning using both pre-trained knowledge and its actual game survival experiences.JARVIS-1 is the existing most general agent in Minecraft, capable of completing over 200 different tasks using control and observation space similar to humans. These tasks range from short-horizon tasks, e.g., “chopping trees” to long-horizon ones, e.g., “obtaining a diamond pickaxe”.JARVIS-1 performs exceptionally well in short-horizon tasks, achieving nearly perfect performance. In the classic long-term task ofObtainDiamondPickaxe,JARVIS-1 surpasses the reliability of current state-of-the-art agents by 5 times and can successfully complete longer-horizon and more challenging tasks. Furthermore, we show thatJARVIS-1 is able toself-improvefollowing a life-long learning paradigm thanks to multimodal memory, sparking a more general intelligence and improved autonomy.

Utilizing large language models (LLMs) to compose off-the-shelf visual tools represents a promising avenue of research for developing robust visual assistants capable of addressing diverse visual tasks. However, these methods often overlook the potential for continual learning, typically by freezing the utilized tools, thus limiting their adaptation to environments requiring new knowledge. To tackle this challenge, we propose CLOVA, a Closed-LOop Visual Assistant, which operates within a framework encompassing inference, reflection, and learning phases. During the inference phase, LLMs generate programs and execute corresponding tools to complete assigned tasks. In the reflection phase, a multimodal global-local reflection scheme analyzes human feedback to determine which tools require updating. Lastly, the learning phase employs three flexible approaches to automatically gather training data and introduces a novel prompt tuning scheme to update the tools, allowing CLOVA to efficiently acquire new knowledge. Experimental findings demonstrate that CLOVA surpasses existing tool-usage methods by 5% in visual question answering and multiple-image reasoning, by 10% in knowledge tagging, and by 20% in image editing. These results under-score the significance of the continual learning capability in general visual assistants.

We study the problem of building a controller that can follow open-ended instructions in open-world environments. We propose to follow reference videos as instructions, which offer expressive goal specifications while eliminating the need for expensive text-gameplay annotations. A new learning framework is derived to allow learning such instruction-following controllers from gameplay videos while producing a video instruction encoder that induces a structured goal space. We implement our agent GROOT in a simple yet effective encoder-decoder architecture based on causal transformers. We evaluate GROOT against open-world counterparts and human players on a proposed Minecraft SkillForge benchmark. The Elo ratings clearly show that GROOT is closing the human-machine gap as well as exhibiting a 70% winning rate over the best generalist agent baseline. Qualitative analysis of the induced goal space further demonstrates some interesting emergent properties, including the goal composition and complex gameplay behavior synthesis.

We introduce Bongard-OpenWorld, a new benchmark for evaluating real-world few-shot reasoning for machine vision. It originates from the classical Bongard Problems (BPs): Given two sets of images (positive and negative), the model needs to identify the set that query images belong to by inducing the visual concepts, which is exclusively depicted by images from the positive set. Our benchmark inherits the few-shot concept induction of the original BPs while adding the two novel layers of challenge: 1) open-world free-form concepts, as the visual concepts in Bongard-OpenWorld are unique compositions of terms from an open vocabulary, ranging from object categories to abstract visual attributes and commonsense factual knowledge; 2) real-world images, as opposed to the synthetic diagrams used by many counterparts. In our exploration, Bongard-OpenWorld already imposes a significant challenge to current few-shot reasoning algorithms. We further investigate to which extent the recently introduced Large Language Models (LLMs) and Vision-Language Models (VLMs) can solve our task, by directly probing VLMs, and combining VLMs and LLMs in an interactive reasoning scheme. We even conceived a neuro-symbolic reasoning approach that reconciles LLMs & VLMs with logical reasoning to emulate the human problem-solving process for Bongard Problems. However, none of these approaches manage to close the human-machine gap, as the best learner achieves 64% accuracy while human participants easily reach 91%. We hope Bongard-OpenWorld can help us better understand the limitations of current visual intelligence and facilitate future research on visual agents with stronger few-shot visual reasoning capabilities.

Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with in-context learning, most VLMs still struggle with understanding complex multi-modal prompts with multiple images, making VLMs less effective in downstream vision-language tasks. In this paper, we address the limitation above by 1) introducing vision-language Model with **M**ulti-**M**odal **I**n-**C**ontext **L**earning(MMICL), a new approach to allow the VLM to deal with multi-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts. Our experiments confirm that MMICL achieves new state-of-the-art zero-shot performance on a wide range of general vision-language tasks, especially for complex benchmarks, including MME and MMBench. Our analysis demonstrates that MMICL effectively tackles the challenge of complex multi-modal prompt understanding and emerges the impressive ICL ability. Furthermore, we observe that MMICL successfully alleviates language bias in VLMs, a common issue for VLMs that often leads to hallucination when faced with extensive textual context. Our code, dataset, dataset tool, and model are available at https://github.com/PKUnlp-icler/MIC.

Leveraging massive knowledge from large language models (LLMs), recent machine learning models show notable successes in general-purpose task solving in diverse domains such as computer vision and robotics. However, several significant challenges remain: (i) most of these models rely on 2D images yet exhibit a limited capacity for 3D input; (ii) these models rarely explore the tasks inherently defined in 3D world, e.g., 3D grounding, embodied reasoning and acting. We argue these limitations significantly hinder current models from performing real-world tasks and approaching general intelligence. To this end, we introduce LEO, an embodied multi-modal generalist agent that excels in perceiving, grounding, reasoning, planning, and acting in the 3D world. LEO is trained with a unified task interface, model architecture, and objective in two stages: (i) 3D vision-language (VL) alignment and (ii) 3D vision-language-action (VLA) instruction tuning. We collect large-scale datasets comprising diverse object-level and scene-level tasks, which require considerable understanding of and interaction with the 3D world. Moreover, we meticulously design an LLM-assisted pipeline to produce high-quality 3D VL data. Through extensive experiments, we demonstrate LEO's remarkable proficiency across a wide spectrum of tasks, including 3D captioning, question answering, embodied reasoning, navigation and manipulation. Our ablative studies and scaling analyses further provide valuable insights for developing future embodied generalist agents. Code and data are available on [project page](https://embodied-generalist.github.io/).

Situation awareness is essential for understanding and reasoning about 3D scenes in embodied AI agents. However, existing datasets and benchmarks for situated understanding suffer from severe limitations in data modality, scope, diversity, and scale. To address these limitations, we propose Multi-modal Situated Question Answering (MSQA), a large-scale multi-modal situated reasoning dataset, scalably collected leveraging 3D scene graphs and vision-language models (VLMs) across a diverse range of real-world 3D scenes. MSQA includes 251K situated questionanswering pairs across 9 distinct question categories, covering complex scenarios and object modalities within 3D scenes. We introduce a novel interleaved multimodal input setting in our benchmark to provide both texts, images, and point clouds for situation and question description, aiming to resolve ambiguity in describing situations with single-modality inputs (e.g., texts). Additionally, we devise the Multi-modal Next-step Navigation (MSNN) benchmark to evaluate models’ grounding of actions and transitions between situations. Comprehensive evaluations on reasoning and navigation tasks highlight the limitations of existing vision-language models and underscore the importance of handling multi-modal interleaved inputs and situation modeling. Experiments on data scaling and crossdomain transfer further demonstrate the effectiveness of leveraging MSQA as a pre-training dataset for developing more powerful situated reasoning models, contributing to advancements in 3D scene understanding for embodied AI.

This paper presents OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in Minecraft. Compared to prior works that either emit textual goals to separate controllers or produce the control command directly, OmniJARVIS seeks a different path to ensure both strong reasoning and efficient decision-making capabilities via unified tokenization of multimodal interaction data. First, we introduce a self-supervised approach to learn a behavior encoder that produces discretized tokens for behavior trajectories $\tau = \{o_0, a_0, \dots\}$ and an imitation learning policy decoder conditioned on these tokens. These additional behavior tokens will be augmented to the vocabulary of pretrained Multimodal Language Models. With this encoder, we then pack long-term multimodal interactions involving task instructions, memories, thoughts, observations, textual responses, behavior trajectories, etc into unified token sequences and model them with autoregressive transformers. Thanks to the semantically meaningful behavior tokens, the resulting VLA model, OmniJARVIS, can reason (by producing chain-of-thoughts), plan, answer questions, and act (by producing behavior tokens for the imitation learning policy decoder). OmniJARVIS demonstrates excellent performances on a comprehensive collection of atomic, programmatic, and open-ended tasks in open-world Minecraft. Our analysis further unveils the crucial design principles in interaction data formation, unified tokenization, and its scaling potentials. The dataset, models, and code will be released at https://craftjarvis.org/OmniJARVIS.

This paper presents UltraEdit, a large-scale (~ 4M editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like InstructPix2Pix and MagicBrush, and provide a systematic approach to producing massive and high-quality image editing samples: 1) UltraEdit includes more diverse editing instructions by combining LLM creativity and in-context editing examples by human raters; 2) UltraEdit is anchored on real images (photographs or artworks), which offers more diversity and less biases than those purely synthesized by text-to-image models; 3) UltraEdit supports region-based editing with high-quality, automatically produced region annotations. Our experiments show that canonical diffusion-based editing baselines trained on UltraEdit set new records on challenging MagicBrush and Emu-Edit benchmarks, respectively. Our analysis further confirms the crucial role of real image anchors and region-based editing data. The dataset, code, and models will be made public.

We study the problem of learning goal-conditioned policies in Minecraft, a popular, widely accessible yet challenging open-ended environment for developing human-level multi-task agents. We first identify two main challenges of learning such policies: 1) the indistinguishability of tasks from the state distribution, due to the vast scene diversity, and 2) the non-stationary nature of environment dynamics caused by partial observability. To tackle the first challenge, we propose Goal-Sensitive Backbone (GSB) for the policy to encourage the emergence of goal-relevant visual state representations. To tackle the second challenge, the policy is further fueled by an adaptive horizon prediction module that helps alleviate the learning uncertainty brought by the non-stationary dynamics. Experiments on 20 Minecraft tasks show that our method significantly outperforms the best baseline so far; in many of them, we double the performance. Our ablation and exploratory studies then explain how our approach beat the counterparts and also unveil the surprising bonus of zero-shot generalization to new scenes (biomes). We hope our agent could help shed some light on learning goal-conditioned, multi-task agents in challenging, open-ended environments like Minecraft. The code is released at https://github.com/CraftJarvis/MC-Controller.

3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence. Current 3D-VL models rely heavily on sophisticated modules, auxiliary losses, and optimization tricks, which calls for a simple and unified model. In this paper, we propose 3D-VisTA, a pre-trained Transformer for 3D Vision and Text Alignment that can be easily adapted to various downstream tasks. 3D-VisTA simply utilizes self-attention layers for both single-modal modeling and multi-modal fusion without any sophisticated task-specific design. To further enhance its performance on 3D-VL tasks, we construct ScanScribe, the first large-scale 3D scene-text pairs dataset for 3D-VL pre-training. ScanScribe contains 2,995 RGB-D scans for 1,185 unique indoor scenes originating from ScanNet and 3R-Scan datasets, along with paired 278K scene descriptions generated from existing 3D-VL tasks, templates, and GPT-3. 3D-VisTA is pre-trained on ScanScribe via masked language/object modeling and scene-text matching. It achieves state-of-the-art results on various 3D-VL tasks, ranging from visual grounding and dense captioning to question answering and situated reasoning. Moreover, 3D-VisTA demonstrates superior data efficiency, obtaining strong performance even with limited annotations during downstream task fine-tuning.

In this paper, we study the problem of planning in Minecraft, a popular, democratized yet challenging open-ended environment for developing multi-task embodied agents. We've found two primary challenges of empowering such agents with planning: 1) planning in an open-ended world like Minecraft requires precise and multi-step reasoning due to the long-term nature of the tasks, and 2) as vanilla planners do not consider the achievability of the current agent when ordering parallel sub-goals within a complicated plan, the resulting plan could be inefficient. To this end, we propose ``$\underline{D}$escribe, $\underline{E}$xplain, $\underline{P}$lan and $\underline{S}$elect'' ($\textbf{DEPS}$), an interactive planning approach based on Large Language Models (LLMs). Our approach helps with better error correction from the feedback during the long-haul planning, while also bringing the sense of proximity via goal $\textbf{Selector}$, a learnable module that ranks parallel sub-goals based on the estimated steps of completion and improves the original plan accordingly. Our experiments mark the milestone of the first zero-shot multi-task agent that can robustly accomplish 70+ Minecraft tasks and nearly double the overall performances. Further testing reveals our method's general effectiveness in popularly adopted non-open-ended domains as well (i.e., ALFWorld and tabletop manipulation). The ablation and exploratory studies detail how our design beats the counterparts and provide a promising update on the $\texttt{ObtainDiamond}$ grand challenge with our approach.

Latent space EBMs, also known as energy-based priors, have drawn growing interests in the field of generative modeling due to its flexibility in the formulation and strong modeling power of the latent space. However, the common practice of learning latent space EBMs with non-convergent short-run MCMC for prior and posterior sampling is hindering the model from further progress; the degenerate MCMC sampling quality in practice often leads to degraded generation quality and instability in training, especially with highly multi-modal and/or high-dimensional target distributions. To remedy this sampling issue, in this paper we introduce a simple but effective diffusion-based amortization method for long-run MCMC sampling and develop a novel learning algorithm for the latent space EBM based on it. We provide theoretical evidence that the learned amortization of MCMC is a valid long-run MCMC sampler. Experiments on several image modeling benchmark datasets demonstrate the superior performance of our method compared with strong counterparts.

A significant gap remains between today's visual pattern recognition models and humanlevel visual cognition especially when it comes to fewshot learning and compositional reasoning of novel concepts. We introduce Bongard-HOI, a new visual reasoning benchmark that focuses on compositional learning of humanobject interactions (HOIs) from natural images. It is inspired by two desirable characteristics from the classical Bongard problems (BPs): 1) fewshot concept learning, and 2) contextdependent reasoning. We carefully curate the fewshot instances with hard negatives, where positive and negative images only disagree on action labels, making mere recognition of object categories insufficient to complete our benchmarks. We also design multiple test sets to systematically study the generalization of visual learning models, where we vary the overlap of the HOI concepts between the training and test sets of fewshot instances, from partial to no overlaps. Bongard-HOI presents a substantial challenge to today's visual recognition models. The state-of-the-art HOI detection model achieves only 62% accuracy on fewshot binary prediction while even amateur human testers on MTurk have 91% accuracy. With the Bongard-HOI benchmark, we hope to further advance research efforts in visual reasoning, especially in holistic perception-reasoning systems and better representation learning.

Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in generative modeling. Fueled by its flexibility in the formulation and strong modeling power of the latent space, recent works built upon it have made interesting attempts aiming at the interpretability of text modeling. However, latent space EBMs also inherit some flaws from EBMs in data space; the degenerate MCMC sampling quality in practice can lead to poor generation quality and instability in training, especially on data with complex latent structures. Inspired by the recent efforts that leverage diffusion recovery likelihood learning as a cure for the sampling issue, we introduce a novel symbiosis between the diffusion models and latent space EBMs in a variational learning framework, coined as the latent diffusion energy-based model. We develop a geometric clustering-based regularization jointly with the information bottleneck to further improve the quality of the learned latent space. Experiments on several challenging tasks demonstrate the superior performance of our model on interpretable text modeling over strong counterparts.

It has been a challenge to learning skills for an agent from long-horizon unannotated demonstrations. Existing approaches like Hierarchical Imitation Learning(HIL) are prone to compounding errors or suboptimal solutions. In this paper, we propose Option-GAIL, a novel method to learn skills at long horizon. The key idea of Option-GAIL is modeling the task hierarchy by options and train the policy via generative adversarial optimization. In particular, we propose an Expectation-Maximization(EM)-style algorithm: an E-step that samples the options of expert conditioned on the current learned policy, and an M-step that updates the low- and high-level policies of agent simultaneously to minimize the newly proposed option-occupancy measurement between the expert and the agent. We theoretically prove the convergence of the proposed algorithm. Experiments show that Option-GAIL outperforms other counterparts consistently across a variety of tasks.

We present Deep Region Competition (DRC), an algorithm designed to extract foreground objects from images in a fully unsupervised manner. Foreground extraction can be viewed as a special case of generic image segmentation that focuses on identifying and disentangling objects from the background. In this work, we rethink the foreground extraction by reconciling energy-based prior with generative image modeling in the form of Mixture of Experts (MoE), where we further introduce the learned pixel re-assignment as the essential inductive bias to capture the regularities of background regions. With this modeling, the foreground-background partition can be naturally found through Expectation-Maximization (EM). We show that the proposed method effectively exploits the interaction between the mixture components during the partitioning process, which closely connects to region competition, a seminal approach for generic image segmentation. Experiments demonstrate that DRC exhibits more competitive performances on complex real-world data and challenging multi-object scenes compared with prior methods. Moreover, we show empirically that DRC can potentially generalize to novel foreground objects even from categories unseen during training.

Learning transferable knowledge across similar but different settings is a fundamental component of generalized intelligence. In this paper, we approach the transfer learning challenge from a causal theory perspective. Our agent is endowed with two basic yet general theories for transfer learning: (i) a task shares a common abstract structure that is invariant across domains, and (ii) the behavior of specific features of the environment remain constant across domains. We adopt a Bayesian perspective of causal theory induction and use these theories to transfer knowledge between environments. Given these general theories, the goal is to train an agent by interactively exploring the problem space to (i) discover, form, and transfer useful abstract and structural knowledge, and (ii) induce useful knowledge from the instance-level attributes observed in the environment. A hierarchy of Bayesian structures is used to model abstract-level structural causal knowledge, and an instance-level associative learning scheme learns which specific objects can be used to induce state changes through interaction. This model-learning scheme is then integrated with a model-based planner to achieve a task in the OpenLock environment, a virtual “escape room” with a complex hierarchy that requires agents to reason about an abstract, generalized causal structure. We compare performances against a set of predominate model-free reinforcement learning (RL) algorithms. RL agents showed poor ability transferring learned knowledge across different trials. Whereas the proposed model revealed similar performance trends as human learners, and more importantly, demonstrated transfer behavior across trials and learning situations.1

In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be perfect and sufficient, which yet is unrealistic to meet in practice. To work on imperfect demonstrations, we first define an imperfect expert setting for RLfD in a formal way, and then point out that previous methods suffer from two issues in terms of optimality and convergence, respectively. Upon the theoretical findings we have derived, we tackle these two issues by regarding the expert guidance as a soft constraint on regulating the policy exploration of the agent, which eventually leads to a constrained optimization problem. We further demonstrate that such problem is able to be addressed efficiently by performing a local linear search on its dual form. Considerable empirical evaluations on a comprehensive collection of benchmarks indicate our method attains consistent improvement over other RLfD counterparts.

In this paper, we present a multimodal mobile teleoperation system that consists of a novel vision-based hand pose regression network (Transteleop) and an IMU (inertial measurement units)-based arm tracking method. Transteleop observes the human hand through a low-cost depth camera and generates not only joint angles but also depth images of paired robot hand poses through an image-to-image translation process. A keypoint-based reconstruction loss explores the resemblance in appearance and anatomy between human and robotic hands and enriches the local features of reconstructed images. A wearable camera holder enables simultaneous hand-arm control and facilitates the mobility of the whole teleoperation system. Network evaluation results on a test dataset and a variety of complex manipulation tasks that go beyond simple pick-and-place operations show the efficiency and stability of our multimodal teleoperation system.

Robust and accurate estimation of liquid height lies as an essential part of pouring tasks for service robots. However, vision-based methods often fail in occluded conditions while audio-based methods cannot work well in a noisy environment. We instead propose a multimodal pouring network (MP-Net) that is able to robustly predict liquid height by conditioning on both audition and haptics input. MP-Net is trained on a self-collected multimodal pouring dataset. This dataset contains 300 robot pouring recordings with audio and force/torque measurements for three types of target containers. We also augment the audio data by inserting robot noise. We evaluated MP-Net on our collected dataset and a wide variety of robot experiments. Both network training results and robot experiments demonstrate that MP-Net is robust against noise and changes to the task and environment. Moreover, we further combine the predicted height and force data to estimate the shape of the target container.

The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactlyrelevant expert demonstrations or the explicitly-coded cost function on target task, both of which, however, are inconvenient to obtain in practice. In this paper, we relax these two strong conditions by developing a novel task transfer framework where the expert preference is applied as a guidance. In particular, we alternate the following two steps: Firstly, letting experts apply pre-defined preference rules to select related expert demonstrates for the target task. Secondly, based on the selection result, we learn the target cost function and trajectory distribution simultaneously via enhanced Adversarial MaxEnt IRL and generate more trajectories by the learned target distribution for the next preference selection. The theoretical analysis on the distribution learning and convergence of the proposed algorithm are provided. Extensive simulations on several benchmarks have been conducted for further verifying the effectiveness of the proposed method.

In this paper, we present TeachNet, a novel neural network architecture for intuitive and markerless vision-based teleoperation of dexterous robotic hands. Robot joint angles are directly generated from depth images of the human hand that produce visually similar robot hand poses in an end-to-end fashion. The special structure of TeachNet, combined with a consistency loss function, handles the differences in appearance and anatomy between human and robotic hands. A synchronized human-robot training set is generated from an existing dataset of labeled depth images of the human hand and simulated depth images of a robotic hand. The final training set includes 400K pairwise depth images and joint angles of a Shadow C6 robotic hand. The network evaluation results verify the superiority of TeachNet, especially regarding the high-precision condition. Imitation experiments and grasp tasks teleoperated by novice users demonstrate that TeachNet is more reliable and faster than the state-of-the-art vision-based teleoperation method.

In this paper, we propose an end-to-end grasp evaluation model to address the challenging problem of localizing robot grasp configurations directly from the point cloud. Compared to recent grasp evaluation metrics that are based on handcrafted depth features and a convolutional neural network (CNN), our proposed PointNetGPD is lightweight and can directly process the 3D point cloud that locates within the gripper for grasp evaluation. Taking the raw point cloud as input, our proposed grasp evaluation network can capture the complex geometric structure of the contact area between the gripper and the object even if the point cloud is very sparse. To further improve our proposed model, we generate a large-scale grasp dataset with 350k real point cloud and grasps with the YCB object set for training. The performance of the proposed model is quantitatively measured both in simulation and on robotic hardware. Experiments on object grasping and clutter removal show that our proposed model generalizes well to novel objects and outperforms state-of-the-art methods. Code and video are available at https://lianghongzhuo.github.io/PointNetGPD.

In this paper, we focus on the challenging perception problem in robotic pouring. Most of the existing approaches either leverage visual or haptic information. However, these techniques may suffer from poor generalization performances on opaque containers or concerning measuring precision. To tackle these drawbacks, we propose to make use of audio vibration sensing and design a deep neural network PouringNet to predict the liquid height from the audio fragment during the robotic pouring task. PouringNet is trained on our collected real-world pouring dataset with multimodal sensing data, which contains more than 3000 recordings of audio, force feedback, video and trajectory data of the human hand that performs the pouring task. Each record represents a complete pouring procedure. We conduct several evaluations on PouringNet with our dataset and robotic hardware. The results demonstrate that our PouringNet generalizes well across different liquid containers, positions of the audio receiver, initial liquid heights and types of liquid, and facilitates a more robust and accurate audio-based perception for robotic pouring.

This paper studies Learning from Observations (LfO) for imitation learning with access to state-only demonstrations. In contrast to Learning from Demonstration (LfD) that involves both action and state supervisions, LfO is more practical in leveraging previously inapplicable resources (e.g., videos), yet more challenging due to the incomplete expert guidance. In this paper, we investigate LfO and its difference with LfD in both theoretical and practical perspectives. We first prove that the gap between LfD and LfO actually lies in the disagreement of inverse dynamics models between the imitator and expert, if following the modeling approach of GAIL. More importantly, the upper bound of this gap is revealed by a negative causal entropy which can be minimized in a model-free way. We term our method as Inverse-Dynamics-Disagreement-Minimization (IDDM) which enhances the conventional LfO method through further bridging the gap to LfD. Considerable empirical results on challenging benchmarks indicate that our method attains consistent improvements over other LfO counterparts.