Vision-language models (VLMs) work well in tasks ranging from image captioning to visual question answering (VQA), yet they struggle with spatial reasoning, a key skill for understanding our physical world that humans excel at. We find that spatial relations are generally rare in widely used VL datasets, with only a few being well represented, while most form a long tail of underrepresented relations. This gap leaves VLMs ill-equipped to handle diverse spatial relationships. To bridge it, we construct a synthetic VQA dataset focused on spatial reasoning generated from hyper-detailed image descriptions in Localized Narratives, DOCCI, and PixMo-Cap. Our dataset consists of 455k samples containing 3.4 million QA pairs. Trained on this dataset, our Spatial-Reasoning Enhanced (SpaRE) VLMs show strong improvements on spatial reasoning benchmarks, achieving up to a 49% performance gain on the What’s Up benchmark, while maintaining strong results on general tasks. Our work narrows the gap between human and VLM spatial reasoning and makes VLMs more capable in real-world tasks such as robotics and navigation. We plan to share our code and dataset in due course.
论文检索
输入标题、作者或关键词，从 2,942 篇学术成果中精准定位
Reinforcement Learning · Deep RL
Reward functions are crucial for policy learning. Large Language Models (LLMs), with strong coding capabilities and valuable domain knowledge, provide an automated solution for high-quality reward design. However, code-based reward functions require precise guiding logic and parameter configurations within a vast design space, leading to low optimization efficiency.To address the challenges,we propose an efficient automated reward design framework, called R*,which decomposes reward design into two parts: reward structure evolution and parameter alignment optimization. To design high-quality reward structures, R* maintains a reward function population and modularizes the functional components. LLMs are employed as the mutation operator, and module-level crossover is proposed to facilitate efficient exploration and exploitation.To design more efficient reward parameters, R* first leverages LLMs to generate multiple critic functions for trajectory comparison and annotation. Based on these critics, a voting mechanism is employed to collect the trajectory segments with high-confidence labels.These labeled segments are then used to refine the reward function parameters through preference learning.Experiments on diverse robotic control tasks demonstrate that R* outperforms strong baselines in both reward design efficiency and quality, surpassing human-designed reward functions.
Reinforcement Learning
Reinforcement learning (RL) in real-world tasks such as robotic navigation often encounters environments with asymmetric traversal costs, where actions like climbing uphill versus moving downhill incur distinctly different penalties, or transitions may become irreversible. While recent quasimetric RL methods relax symmetry assumptions, they typically do not explicitly account for path-dependent costs or provide rigorous safety guarantees. We introduce Quasi-Potential Reinforcement Learning (QPRL), a novel framework that explicitly decomposes asymmetric traversal costs into a path-independent potential function ($\Phi$) and a path-dependent residual ($\Psi$). This decomposition allows efficient learning and stable policy optimization via a Lyapunov-based safety mechanism. Theoretically, we prove that QPRL achieves convergence with improved sample complexity of $\tilde{O}(\sqrt{T})$, surpassing prior quasimetric RL bounds of $\tilde{O}(T)$. Empirically, our experiments demonstrate that QPRL attains state-of-the-art performance across various navigation and control tasks, significantly reducing irreversible constraint violations by approximately $4\times$ compared to baselines.
Theory · Game Theory
Behavioral diversity, expert imitation, fairness, safety goals and others give rise to preferences in sequential decision making domains that do not decompose additively across time. We introduce the class of convex Markov games that allow general convex preferences over occupancy measures. Despite infinite time horizon and strictly higher generality than Markov games, pure strategy Nash equilibria exist. Furthermore, equilibria can be approximated empirically by performing gradient descent on an upper bound of exploitability. Our experiments reveal novel solutions to classic repeated normal-form games, find fair solutions in a repeated asymmetric coordination game, and prioritize safe long-term behavior in a robot warehouse environment. In the prisoner's dilemma, our algorithm leverages transient imitation to find a policy profile that deviates from observed human play only slightly, yet achieves higher per-player utility while also being three orders of magnitude less exploitable.
Reinforcement Learning · Policy Search
This paper addresses the challenge of discontinuity in goal-achievement capabilities observed in Goal-conditioned Reinforcement Learning (GCRL) algorithms. Through a theoretical analysis, we identify that the reuse of successful trajectories or policies during training can aid in achieving adjacent goals of achievable goals. However, the policy discrepancy between achievable and adjacent goals must be carefully managed to avoid both overly trivial and excessively large differences, which can respectively hinder policy performance. To tackle this issue, we propose a margin-based policy self-regularization approach that optimizes the policy discrepancies between adjacent desired goals to a minimal acceptable threshold. This method can be integrated into popular GCRL algorithms, such as GC-SAC, HER, and GC-PPO. Systematic evaluations across two robotic arm control tasks and a complex fixed-wing aircraft control task demonstrate that our approach significantly improves the continuity of goal-achievement abilities of GCRL algorithms, thereby enhancing their overall performance.
Applications · Robotics
Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert demonstrations.To address these shortcomings, we propose Latent Diffusion Planning (LDP), a modular approach consisting of a planner which can leverage action-free demonstrations, and an inverse dynamics model which can leverage suboptimal data, that both operate over a learned latent space. First, we learn a compact latent space through a variational autoencoder, enabling effective forecasting of future states in image-based domains. Then, we train a planner and an inverse dynamics model with diffusion objectives. By separating planning from action prediction, LDP can benefit from the denser supervision signals of suboptimal and action-free data.On simulated visual robotic manipulation tasks, LDP outperforms state-of-the-art imitation learning approaches, as they cannot leverage such additional data.
Applications · Robotics
We propose CAL (Complete Anything in Lidar) for Lidar-based shape-completion in-the-wild. This is closely related to Lidar-based semantic/panoptic scene completion. However, contemporary methods can only complete and recognize objects from a closed vocabulary labeled in existing Lidar datasets. Different to that, our zero-shot approach leverages the temporal context from multi-modal sensor sequences to mine object shapes and semantic features of observed objects. These are then distilled into a Lidar-only instance-level completion and recognition model. Although we only mine partial shape completions, we find that our distilled model learns to infer full object shapes from multiple such partial observations across the dataset. We show that our model can be prompted on standard benchmarks for Semantic and Panoptic Scene Completion, localize objects as (amodal) 3D bounding boxes, and recognize objects beyond fixed class vocabularies.
Reinforcement Learning · Batch/Offline
This paper proposes Constrained Exploitability Descent (CED), a model-free offline reinforcement learning (RL) algorithm for solving adversarial Markov games (MGs). CED combines the game-theoretical approach of Exploitability Descent (ED) with policy constraint methods from offline RL. While policy constraints can perturb the optimal pure-strategy solutions in single-agent scenarios, we find the side effect less detrimental in adversarial games, where the optimal policy can be a mixed-strategy Nash equilibrium. We theoretically prove that, under the uniform coverage assumption on the dataset, CED converges to a stationary point in deterministic two-player zero-sum Markov games. We further prove that the min-player policy at the stationary point follows the property of mixed-strategy Nash equilibrium in MGs. Compared to the model-based ED method that optimizes the max-player policy, our CED method no longer relies on a generalized gradient. Experiments in matrix games, a tree-form game, and an infinite-horizon soccer game verify that CED can find an equilibrium policy for the min-player as long as the offline dataset guarantees uniform coverage. Besides, CED achieves a significantly lower NashConv compared to an existing pessimism-based method and can gradually improve the behavior policy even under non-uniform data coverages. When combined with neural networks, CED also outperforms behavior cloning and offline self-play in a large-scale two-team robotic combat game.
Reinforcement Learning · Batch/Offline
Offline reinforcement learning (RL) enables policy optimization using static datasets, avoiding the risks and costs of extensive real-world exploration. However, it struggles with suboptimal offline behaviors and inaccurate value estimation due to the lack of environmental interaction. We present Video-Enhanced Offline RL (VeoRL), a model-based method that constructs an interactive world model from diverse, unlabeled video data readily available online. Leveraging model-based behavior guidance, our approach transfers commonsense knowledge of control policy and physical dynamics from natural videos to the RL agent within the target domain. VeoRL achieves substantial performance gains (over 100% in some cases) across visual control tasks in robotic manipulation, autonomous driving, and open-world video games. Project page: https://panmt.github.io/VeoRL.github.io.
Theory · Learning Theory
In Reinforcement Learning (RL), tasks with instantaneous hard constraints present significant challenges, particularly when the decision space is non-convex or non-star-convex. This issue is especially relevant in domains like autonomous vehicles and robotics, where constraints such as collision avoidance often take a non-convex form. In this paper, we establish a regret bound of $\tilde{\mathcal{O}}((1 + \tfrac{1}{\tau}) \sqrt{\log(\frac{1}{\tau}) d^3 H^4 K})$, applicable to both star-convex and non-star-convex cases, where $d$ is the feature dimension, $H$ the episode length, $K$ the number of episodes, and $\tau$ the safety threshold. Moreover, the violation of safety constraints is zero with high probability throughout the learning process. A key technical challenge in these settings is bounding the covering number of the value-function class, which is essential for achieving value-aware uniform concentration in model-free function approximation. For the star-convex setting, we develop a novel technique called *Objective–Constraint Decomposition* (OCD) to properly bound the covering number. This result also resolves an error in a previous work on constrained RL. In non-star-convex scenarios, where the covering number can become infinitely large, we propose a two-phase algorithm, Non-Convex Safe Least Squares Value Iteration (NCS-LSVI), which first reduces uncertainty about the safe set by playing a known safe policy. After that, it carefully balances exploration and exploitation to achieve the regret bound. Finally, numerical simulations on an autonomous driving scenario demonstrate the effectiveness of NCS-LSVI.
Applications · Language, Speech and Dialog
Feedback from peer review is essential to improve the quality of scientific articles. However, at present, many manuscripts do not receive sufficient external feedback for refinement before or during submission. Therefore, a system capable of providing detailed and professional feedback is crucial for enhancing research efficiency. In this paper, we have compiled the largest dataset of paper reviews to date by collecting historical open-access papers and their corresponding review comments and standardizing them using LLM. We then developed a multi-agent system that mimics real human review processes, based on LLMs. This system, named Agent Reviewers, includes the innovative introduction of multimodal reviewers to provide feedback on the visual elements of papers. Additionally, a shared memory pool that stores historical papers' metadata is preserved, which supplies reviewer agents with background knowledge from different fields. Our system is evaluated using ICLR 2024 papers and achieves superior performance compared to existing AI-based review systems. Comprehensive ablation studies further demonstrate the effectiveness of each module and agent in this system.
Theory · Learning Theory
Actor-critic algorithms have been instrumental in boosting the performance of numerous challenging applications involving continuous control, such as highly robust and agile robot motion control. However, their theoretical understanding remains largely underdeveloped. Existing analyses mostly focus on finite state-action spaces and on simplified variants of actor-critic, such as double-loop updates with i.i.d. sampling, which are often impractical for real-world applications.We consider the canonical and widely adopted single-timescale updates with Markovian sampling in continuous state-action space. Specifically, we establish finite-time convergence by introducing a novel Lyapunov analysis framework, which provides a unified convergence characterization of both the actor and the critic. Our approach is less conservative than previous methods and offers new insights into the coupled dynamics of actor-critic updates.
Deep Learning
Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation.Existing approaches mainly leverage latent variable models, e.g., VQ-VAE, to learn skill abstractions through learned vectors (codebooks), while they suffer from codebook collapse and modeling the causal relationship between learned skills. To address these limitations, we present **S**kill **T**raining with **A**ugmented **R**otation (**STAR**), a framework that advances both skill learning and composition to complete complex behaviors. Specifically, to prevent codebook collapse, we devise rotation-augmented residual skill quantization (RaRSQ).It encodes relative angles between encoder outputs into the gradient flow by rotation-based gradient mechanism. Points within the same skill code are forced to be either pushed apart or pulled closer together depending on gradient directions.Further, to capture the casual relationship between skills, we present causal skill transformer (CST) which explicitly models dependencies between skill representations through an autoregressive mechanism for coherent action generation.Extensive experiments demonstrate the superiority of STAR on both LIBERO benchmark and realworld tasks, with around 12% improvement over the baselines.
General Machine Learning · Everything Else
Learning unknown dynamics under environmental (or external) constraints is fundamental to many fields (e.g., modern robotics), particularly challenging when constraint information is only locally available and uncertain. Existing approaches requiring global constraints or using probabilistic filtering fail to fully exploit the geometric structure inherent in local measurements (by using, e.g., sensors) and constraints. This paper presents a geometric framework unifying measurements, constraints, and dynamics learning through a fiber bundle structure over the state space. This naturally induced geometric structure enables measurement-aware Control Barrier Functions that adapt to local sensing (or measurement) conditions. By integrating Neural ODEs, our framework learns continuous-time dynamics while preserving geometric constraints, with theoretical guarantees of learning convergence and constraint satisfaction dependent on sensing quality. The geometric framework not only enables efficient dynamics learning but also suggests promising directions for integration with reinforcement learning approaches. Extensive simulations demonstrate significant improvements in both learning efficiency and constraint satisfaction over traditional methods, especially under limited and uncertain sensing conditions.
Applications · Robotics
The effectiveness of scaling up training data in robotic manipulation is still limited. A primary challenge in manipulation is the tasks are diverse, and the trained policy would be confused if the task targets are not specified clearly. Existing works primarily rely on text instruction to describe targets. However, we reveal that current robotic data cannot train policies to understand text instruction effectively, and vision is much more comprehensible. Therefore, we introduce utilizing vision instruction to specify targets. A straightforward implementation is training a policy to predict the intermediate actions linking the current observation and a future image. Nevertheless, a single future image does not describe the task target in insufficient detail. To handle this problem, we propose to use sparse point flows to provide more detailed information. Extensive tasks are designed based on real and simulated environments to evaluate the effectiveness of our vision instructed pre-training (VIP) method. The results indicate VIP improves the performance on diverse tasks significantly, and the derived policy can complete competitive tasks like ``opening the lid of a tightly sealed bottle''.
Reinforcement Learning
Many dynamic decision problems, such as robotic control, involve a series of tasks, many of which are unknown at training time.Typical approaches for these problems, such as multi-task and meta reinforcement learning, do not generalize well when the tasks are diverse. On the other hand, approaches that aim to tackle task diversity, such as using task embedding as policy context and task clustering, typically lack performance guarantees and require a large number of training tasks. To address these challenges, we propose a novel approach for learning a policy committee that includes at least one near-optimal policy with high probability for tasks encountered during execution. While we show that this problem is in general inapproximable, we present two practical algorithmic solutions.The first yields provable approximation and task sample complexity guarantees when tasks are low-dimensional (the best we can do due to inapproximability), whereas the second is a general and practical gradient-based approach. In addition, we provide a provable sample complexity bound for few-shot learning. Our experiments on MuJoCo and Meta-World show that the proposed approach outperforms state-of-the-art multi-task, meta-, and task clustering baselines in training, generalization, and few-shot learning, often by a large margin. Our code is available at https://github.com/CERL-WUSTL/PACMAN.
Applications · Robotics
Vision-Language-Action (VLA) models aim to predict robotic actions based on visual observations and language instructions. Existing approaches require fine-tuning pre-trained vision-language models (VLMs) as visual and language features are independently fed into downstream policies, degrading the pre-trained semantic alignments. We propose OTTER, a novel VLA architecture that leverages these existing alignments through explicit, text-aware visual feature extraction. Instead of processing all visual features, OTTER selectively extracts and passes only task-relevant visual features that are semantically aligned with the language instruction to the policy transformer. This allows OTTER to keep the pre-trained vision-language encoders frozen. Thereby, OTTER preserves and utilizes the rich semantic understanding learned from large-scale pre-training, enabling strong zero-shot generalization capabilities. In simulation and real-world experiments, OTTER significantly outperforms existing VLA models, demonstrating strong zero-shot generalization to novel objects and environments. Video, code, checkpoints, and dataset: https://ottervla.github.io/.
Applications · Robotics
As autonomous systems become more ubiquitous in daily life, ensuring high performance with guaranteed safety is crucial. However, safety and performance could be competing objectives, which makes their co-optimization difficult. Learning-based methods, such as Constrained Reinforcement Learning (CRL), achieve strong performance but lack formal safety guarantees due to safety being enforced as soft constraints, limiting their use in safety-critical settings. Conversely, formal methods such as Hamilton-Jacobi (HJ) Reachability Analysis and Control Barrier Functions (CBFs) provide rigorous safety assurances but often neglect performance, resulting in overly conservative controllers. To bridge this gap, we formulate the co-optimization of safety and performance as a state-constrained optimal control problem, where performance objectives are encoded via a cost function and safety requirements are imposed as state constraints. We demonstrate that the resultant value function satisfies a Hamilton-Jacobi-Bellman (HJB) equation, which we approximate efficiently using a novel physics-informed machine learning framework. In addition, we introduce a conformal prediction-based verification strategy to quantify the learning errors, recovering a high-confidence safety value function, along with a probabilistic error bound on performance degradation. Through several case studies, we demonstrate the efficacy of the proposed framework in enabling scalable learning of safe and performant controllers for complex, high-dimensional autonomous systems.
Applications · Robotics
We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up our model parameters and training data by multiple orders of magnitude, enabling us to explore the scaling properties in terms of dataset size, model parameters, and compute. We evaluate DriveGPT across different scales in a planning task, through both quantitative metrics and qualitative examples, including closed-loop driving in complex real-world scenarios. In a separate prediction task, DriveGPT outperforms state-of-the-art baselines and exhibits improved performance by pretraining on a large-scale dataset, further validating the benefits of data scaling.
Applications · Robotics
Shape assembly, the process of combining parts into a complete whole, is a crucial skill for robots with broad real-world applications. Among the various assembly tasks, geometric assembly—where broken parts are reassembled into their original form (e.g., reconstructing a shattered bowl)—is particularly challenging. This requires the robot to recognize geometric cues for grasping, assembly, and subsequent bimanual collaborative manipulation on varied fragments. In this paper, we exploit the geometric generalization of point-level affordance, learning affordance aware of bimanual collaboration in geometric assembly with long-horizon action sequences. To address the evaluation ambiguity caused by geometry diversity of broken parts, we introduce a real-world benchmark featuring geometric variety and global reproducibility. Extensive experiments demonstrate the superiority of our approach over both previous affordance-based and imitation-based methods.