Attention-based Learning for 3D Informative Path Planning

In this work, we propose an attention-based deep reinforcement learning approach to address the adaptive informative path planning (IPP) problem in 3D space, where an aerial robot equipped with a downward-facing sensor must dynamically adjust its 3D position to balance sensing footprint and accuracy, and finally obtain a high-quality belief of an underlying field of interest over a given domain (e.g., presence of specific plants, hazardous gas, geological structures, etc.). In adaptive IPP tasks, the agent is tasked with maximizing information collected under time/distance constraints, continuously adapting its path based on newly acquired sensor data. To this end, we leverage attention mechanisms for their strong ability to capture global spatial dependencies across large action spaces, allowing the agent to learn an implicit estimation of environmental transitions. Our model builds a contextual belief representation over the entire domain, guiding sequential movement decisions that optimize both short- and long-term search objectives. Comparative evaluations against state-of-the-art planners demonstrate that our approach significantly reduces environmental uncertainty within constrained budgets, thus allowing the agent to effectively balance exploration and exploitation. We further show our model generalizes well to environments of varying sizes, highlighting its potential for many real-world applications.

Search-TTA: A Multimodal Test-Time Adaptation Framework for Visual Search in the Wild

To perform autonomous visual search for environmental monitoring, a robot may leverage satellite imagery as a prior map. This can help inform coarse, high-level search and exploration strategies, even when such images lack sufficient resolution to allow fine-grained, explicit visual recognition of targets. However, there are some challenges to overcome with using satellite images to direct visual search. For one, targets that are unseen in satellite images are underrepresented (compared to ground images) in most existing datasets, and thus vision models trained on these datasets fail to reason effectively based on indirect visual cues. Furthermore, approaches which leverage large Vision Language Models (VLMs) for generalization may yield inaccurate outputs due to hallucination, leading to inefficient search. To address these challenges, we introduce Search-TTA, a multimodal test-time adaptation framework that can accept text and/or image input. First, we pretrain a remote sensing image encoder to align with CLIP's visual encoder to output probability distributions of target presence used for visual search. Second, our framework dynamically refines CLIP's predictions during search using a test-time adaptation mechanism. Through a feedback loop inspired by Spatial Poisson Point Processes, gradient updates (weighted by uncertainty) are used to correct (potentially inaccurate) predictions and improve search performance. To validate Search-TTA's performance, we curate a visual search dataset based on internet-scale ecological data. We find that Search-TTA improves planner performance by up to 9.7%, particularly in cases with poor initial CLIP predictions. It also achieves comparable performance to state-of-the-art VLMs. Finally, we deploy Search-TTA on a real UAV via hardware-in-the-loop testing, by simulating its operation within a large-scale simulation that provides onboard sensing.

APEX: Action Priors Enable Efficient Exploration for Skill Imitation on Articulated Robots

Learning by imitation provides an effective way for robots to develop well-regulated complex behaviors and directly benefit from natural demonstrations. State-of-the-art imitation learning (IL) approaches typically leverage Adversarial Motion Priors (AMP), which, despite their impressive results, suffer from two key limitations. They are prone to mode collapse, which often leads to overfitting to the simulation environment and thus increased sim-to-real gap, and they struggle to learn diverse behaviors effectively. To overcome these limitations, we introduce APEX (Action Priors enable Efficient eXploration): a simple yet versatile imitation learning framework that integrates demonstrations directly into reinforcement learning (RL), maintaining high exploration while grounding behavior with expert-informed priors. We achieve this through a combination of decaying action priors, which initially bias exploration toward expert demonstrations but gradually allow the policy to explore independently. This is complemented by a multi-critic RL framework that effectively balances stylistic consistency with task performance. Our approach achieves sample-efficient imitation learning and enables the acquisition of diverse skills within a single policy. APEX generalizes to varying velocities and preserves reference-like styles across complex tasks such as navigating rough terrain and climbing stairs, utilizing only flat-terrain kinematic motion data as a prior. We validate our framework through extensive hardware experiments on the Unitree Go2 quadruped. There, APEX yields diverse and agile locomotion gaits, inherent gait transitions, and the highest reported speed for the platform to the best of our knowledge (peak velocity of ~3.3 m/s on hardware). Our results establish APEX as a compelling alternative to existing IL methods, offering better efficiency, adaptability, and real-world performance.

Latent Theory of Mind: A Decentralized Diffusion Architecture for Cooperative Manipulation

We present Latent Theory of Mind (LatentToM), a decentralized diffusion policy architecture for collaborative robot manipulation. Our policy allows multiple manipulators with their own perception and computation to collaborate with each other towards a common task goal with or without explicit communication. Our key innovation lies in allowing each agent to maintain two latent representations: an ego embedding specific to the robot, and a consensus embedding trained to be common to both robots, despite their different sensor streams and poses. We further let each robot train a decoder to infer the other robot's ego embedding from their consensus embedding, akin to theory of mind in latent space. Training occurs centrally, with all the policies' consensus encoders supervised by a loss inspired by sheaf theory, a mathematical theory for clustering data on a topological manifold. Specifically, we introduce a first-order cohomology loss to enforce sheaf-consistent alignment of the consensus embeddings. To preserve the expressiveness of the consensus embedding, we further propose structural constraints based on theory of mind and a directional consensus mechanism. Execution can be fully distributed, requiring no explicit communication between policies. In which case, the information is exchanged implicitly through each robot's sensor stream by observing the actions of the other robots and their effects on the scene. Alternatively, execution can leverage direct communication to share the robots' consensus embeddings, where the embeddings are shared once during each inference step and are aligned using the sheaf Laplacian. In our hardware experiments, LatentToM outperforms a naive decentralized diffusion baseline, and shows comparable performance with a state-of-the-art centralized diffusion policy for bi-manual manipulation. Project website: https://stanfordmsl.github.io/LatentToM/.

Demystifying Diffusion Policies: Action Memorization and Simple Lookup Table Alternatives

Diffusion policies have demonstrated remarkable dexterity and robustness in intricate, high-dimensional robot manipulation tasks, while training from a small number of demonstrations. However, the reason for this performance remains a mystery. In this paper, we offer a surprising hypothesis: diffusion policies essentially memorize an action lookup table -- and this is beneficial. We posit that, at runtime, diffusion policies find the closest training image to the test image in a latent space, and recall the associated training action sequence, offering reactivity without the need for action generalization. This is effective in the sparse data regime, where there is not enough data density for the model to learn action generalization. We support this claim with systematic empirical evidence. Even when conditioned on wildly out of distribution (OOD) images of cats and dogs, the Diffusion Policy still outputs an action sequence from the training data. With this insight, we propose a simple policy, the Action Lookup Table (ALT), as a lightweight alternative to the Diffusion Policy. Our ALT policy uses a contrastive image encoder as a hash function to index the closest corresponding training action sequence, explicitly performing the computation that the Diffusion Policy implicitly learns. We show empirically that for relatively small datasets, ALT matches the performance of a diffusion model, while requiring only 0.0034 of the inference time and 0.0085 of the memory footprint, allowing for much faster closed-loop inference with resource constrained robots. We also train our ALT policy to give an explicit OOD flag when the distance between the runtime image is too far in the latent space from the training images, giving a simple but effective runtime monitor. More information can be found at: https://stanfordmsl.github.io/alt/.

Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control

Adaptive traffic signal control (ATSC) is crucial in reducing congestion, maximizing throughput, and improving mobility in rapidly growing urban areas. Recent advancements in parameter-sharing multi-agent reinforcement learning (MARL) have greatly enhanced the scalable and adaptive optimization of complex, dynamic flows in large-scale homogeneous networks. However, the inherent heterogeneity of real-world traffic networks, with their varied intersection topologies and interaction dynamics, poses substantial challenges to achieving scalable and effective ATSC across different traffic scenarios. To address these challenges, we present Unicorn, a universal and collaborative MARL framework designed for efficient and adaptable network-wide ATSC. Specifically, we first propose a unified approach to map the states and actions of intersections with varying topologies into a common structure based on traffic movements. Next, we design a Universal Traffic Representation (UTR) module with a decoder-only network for general feature extraction, enhancing the model's adaptability to diverse traffic scenarios. Additionally, we incorporate an Intersection Specifics Representation (ISR) module, designed to identify key latent vectors that represent the unique intersection's topology and traffic dynamics through variational inference techniques. To further refine these latent representations, we employ a contrastive learning approach in a self-supervised manner, which enables better differentiation of intersection-specific features. Moreover, we integrate the state-action dependencies of neighboring agents into policy optimization, which effectively captures dynamic agent interactions and facilitates efficient regional collaboration. Our results show that Unicorn outperforms other methods across various evaluation metrics, highlighting its potential in complex, dynamic traffic networks.

HELM: Human-Preferred Exploration with Language Models

In autonomous exploration tasks, robots are required to explore and map unknown environments while efficiently planning in dynamic and uncertain conditions. Given the significant variability of environments, human operators often have specific preference requirements for exploration, such as prioritizing certain areas or optimizing for different aspects of efficiency. However, existing methods struggle to accommodate these human preferences adaptively, often requiring extensive parameter tuning or network retraining. With the recent advancements in Large Language Models (LLMs), which have been widely applied to text-based planning and complex reasoning, their potential for enhancing autonomous exploration is becoming increasingly promising. Motivated by this, we propose an LLM-based human-preferred exploration framework that seamlessly integrates a mobile robot system with LLMs. By leveraging the reasoning and adaptability of LLMs, our approach enables intuitive and flexible preference control through natural language while maintaining a task success rate comparable to state-of-the-art traditional methods. Experimental results demonstrate that our framework effectively bridges the gap between human intent and policy preference in autonomous exploration, offering a more user-friendly and adaptable solution for real-world robotic applications.

SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learning

Despite recent advances in learning-based controllers for legged robots, deployments in human-centric environments remain limited by safety concerns. Most of these approaches use position-based control, where policies output target joint angles that must be processed by a low-level controller (e.g., PD or impedance controllers) to compute joint torques. Although impressive results have been achieved in controlled real-world scenarios, these methods often struggle with compliance and adaptability when encountering environments or disturbances unseen during training, potentially resulting in extreme or unsafe behaviors. Inspired by how animals achieve smooth and adaptive movements by controlling muscle extension and contraction, torque-based policies offer a promising alternative by enabling precise and direct control of the actuators in torque space. In principle, this approach facilitates more effective interactions with the environment, resulting in safer and more adaptable behaviors. However, challenges such as a highly nonlinear state space and inefficient exploration during training have hindered their broader adoption. To address these limitations, we propose SATA, a bio-inspired framework that mimics key biomechanical principles and adaptive learning mechanisms observed in animal locomotion. Our approach effectively addresses the inherent challenges of learning torque-based policies by significantly improving early-stage exploration, leading to high-performance final policies. Remarkably, our method achieves zero-shot sim-to-real transfer. Our experimental results indicate that SATA demonstrates remarkable compliance and safety, even in challenging environments such as soft/slippery terrain or narrow passages, and under significant external disturbances, highlighting its potential for practical deployments in human-centric and safety-critical scenarios.

MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation

The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances in reasoning models and shifts in scaling laws, we pioneer bringing test-time computation into LLM-as-a-Judge, proposing MCTS-Judge, a resource-efficient, System-2 thinking framework for code correctness evaluation. MCTS-Judge leverages Monte Carlo Tree Search (MCTS) to decompose problems into simpler, multi-perspective evaluations. Through a node-selection strategy that combines self-assessment based on historical actions in the current trajectory and the Upper Confidence Bound for Trees based on prior rollouts, MCTS-Judge balances global optimization and refinement of the current trajectory. We further designed a high-precision, unit-test-level reward mechanism to encourage the Large Language Model (LLM) to perform line-by-line analysis. Extensive experiments on three benchmarks and five LLMs demonstrate the effectiveness of MCTS-Judge, which improves the base model's accuracy from 41% to 80%, surpassing the o1-series models with 3x fewer tokens. Further evaluations validate the superiority of its reasoning trajectory in logic, analytics, thoroughness, and overall quality, while revealing the test-time scaling law of the LLM-as-a-Judge paradigm.

SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding

The Multi-Agent Path Finding (MAPF) problem aims to determine the shortest and collision-free paths for multiple agents in a known, potentially obstacle-ridden environment. It is the core challenge for robotic deployments in large-scale logistics and transportation. Decentralized learning-based approaches have shown great potential for addressing the MAPF problems, offering more reactive and scalable solutions. However, existing learning-based MAPF methods usually rely on agents making decisions based on a limited field of view (FOV), resulting in short-sighted policies and inefficient cooperation in complex scenarios. There, a critical challenge is to achieve consensus on potential movements between agents based on limited observations and communications. To tackle this challenge, we introduce a new framework that applies sheaf theory to decentralized deep reinforcement learning, enabling agents to learn geometric cross-dependencies between each other through local consensus and utilize them for tightly cooperative decision-making. In particular, sheaf theory provides a mathematical proof of conditions for achieving global consensus through local observation. Inspired by this, we incorporate a neural network to approximately model the consensus in latent space based on sheaf theory and train it through self-supervised learning. During the task, in addition to normal features for MAPF as in previous works, each agent distributedly reasons about a learned consensus feature, leading to efficient cooperation on pathfinding and collision avoidance. As a result, our proposed method demonstrates significant improvements over state-of-the-art learning-based MAPF planners, especially in relatively large and complex scenarios, demonstrating its superiority over baselines in various simulations and real-world robot experiments.