Stanford HAI

VLAs aren't just memorizing training data; sparse autoencoders reveal a hidden layer of generalizable motion primitives that can be steered to control robot behavior across tasks.

Robots often ignore your commands mid-task, but ReSteer offers a way to fix this by pinpointing and patching the "blind spots" in their training data.

Encoding deformable object dynamics with particle positions unlocks sim-to-real transfer for manipulation tasks, achieving impressive real-world success rates.

Stochastic resetting—randomly teleporting RL agents back to the start—surprisingly speeds up learning, even when it wouldn't help a non-learning agent.

Forget slow, model-dependent curation: FAKTUAL offers a fast, model-free way to boost robot imitation learning by directly maximizing the entropy of demonstration datasets.

A robot can now play recognizable piano songs after just 30 minutes of real-world training, closing the sim-to-real gap for high-precision bimanual manipulation.

RADAR offers a scalable, interpretable framework for understanding robot policy generalization by directly linking test-time performance to the training data, revealing the specific types of generalization required.

Semi-decentralized POMDPs offer a unifying framework that subsumes decentralized and multiagent POMDPs, enabling a more nuanced approach to communication constraints in multi-agent systems.

Ditch the anchors and NMS: AutoReg3D reimagines 3D object detection as a sequence generation problem, opening the door for language-model techniques in 3D perception.

Forget retraining: you can steer a robot's behavior in real-time by nudging its internal representations with lightweight, targeted interventions.

Robots can now remember what they've done and what they need to do next for 15 minutes straight, thanks to a new memory architecture that mixes video and text.

Turns out, the best memory design for robotic manipulation depends heavily on the task, with no single architecture dominating across the board.

Unlock compliant robot control without force sensors or complex learning, using only motor signals already available in most modern robots.

By unifying hand motion estimation and generation into a single diffusion framework, UniHand handles heterogeneous inputs and challenging conditions like occlusions better than task-specific models.

Robots can now learn from their mistakes in real-time via a novel reflective planning framework, leading to significant performance gains in long-horizon tasks.

Diffusion models can efficiently sample lookahead action sequences for active search, outperforming traditional tree search while mitigating optimism bias.

Robots can now navigate complex outdoor environments and find objects using natural language queries, even without prior maps or precise depth sensing.

XR gets real: control virtual worlds with your head and hands, not just text prompts.

Autonomous inspection robots can now anticipate failures and anomalies in real-time with over 90% accuracy, even before a human observer can react.

A single RL policy trained on procedurally generated tools in simulation can achieve zero-shot dexterous manipulation of diverse real-world tools, rivaling task-specific policies.

Factored world models can disentangle the dynamics of multiple interacting entities, leading to more controllable video generation and improved policy learning.

Forget synthetic data—scaling up human egocentric video by 20x unlocks surprisingly effective dexterous robot manipulation, even transferring to robots with different hand configurations.

Verification at test time can be a surprisingly effective alternative to scaling policy learning for vision-language-action alignment, yielding substantial gains in both simulated and real-world robotic tasks.

Closing the reality gap: iteratively refining a world model with real-world robot data yields a significant boost in vision-language-action policy performance.

A unified Vision-Language Model and Diffusion architecture unlocks surprisingly effective optical flow forecasting from noisy web data, enabling language-conditioned robot control and video generation.

A novel long-reach robot arm overcomes structural instability to thread cables with centimeter precision, unlocking new possibilities for autonomous lunar construction.

Q-functions and implicit policy extraction are game-changers for batch online RL in robotics, unlocking significant performance gains over imitation-based approaches.

An end-to-end learned robotic system can now clean your kitchen in a completely new house, thanks to a novel co-training approach on diverse data.