Category
1,589 papers
It is demonstrated that high natural-trajectory accuracy can coexist with weak controlled target-state responsiveness in fixed representation-readout pairs and adding responsiveness and context sensitivity to a failure predictor reduces policy-failure prediction error on new initializations relative to the specified ba...
These results motivate reproducible accumulation, finite-difference validation that compares perturbation-induced loss changes with repeated-run variation, and explicit reporting of objective construction when differentiable simulation is used for robotic optimization.
The Agentic Reward System (ARS) is introduced, an inference framework for progress reward modeling with general-purpose vision-language models (VLMs), without additional reward-model training, and its results suggest that structured inference and verification can improve the usefulness of general-purpose VLMs for robot...
World models for manipulation are typically trained from video, yet the events that determine how manipulation unfolds, such as making and releasing contact, are difficult to observe visually and are often easier to sense through touch. We present the Dexterous Tactile World Model (DTWM), a video world model for future...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Across 30 RoboDojo tasks, using zero shot for Open and one demonstration elsewhere, RoboICL improves on official zero-shot \gptastra{} by 20--27 progress-score points in every category, and leads the leaderboard baselines on Memory and Open, achieves comparable performance to the strongest Precision baseline, and remai...
This paper proposes a 3D point tracker accurate in those absolute terms and operating within a single commodity GPU, pose-free, monocular budget, exceeding strong feed-forward trackers and a companion analysis explains why several published trackers lose most of their accuracy under this budget.
A visual state estimator is trained using both direct state supervision and an action-consistency loss backpropagated through the frozen, differentiable expert, which consistently outperforms direct pixel-to-action imitation from the same expert demonstration corpus.
This work decomposes multi-step rollout error into the errors introduced at individual steps and their propagation through subsequent transitions, showing that state-affine dynamics are precisely the differentiable transitions with state-independent Jacobians, eliminating the nonlinear propagation residual and making t...
This work evolves freeform robots to pick up, hold, rotate, and use diverse objects, and uses contrastive learning to create a highly searchable genetic embedding of design space, an autoregressive developmental model to decode designs, evolutionary strategies to find good designs, and reinforcement learning to train e...
A graph-attention network that reads the current and proposed states of moving agents together with locally relevant stationary obstacles and returns one collision-risk score per moving agent, which any controller can use to accept, repair, replan, or postpone a proposed step.
Copper-Policy is introduced, which learns a compact World representation with the policy rather than relying on a predefined target space and predicts future observation embeddings conditioned on task intention without reconstructing pixels through temporal joint-embedding prediction.
A controlled empirical study of which design choices allow visuomotor policies to generalize across viewpoints finds that viewpoint generalization improves when dense visual tokens are retained and the action head participates in geometric reasoning.
A Blog post by Ai2 on Hugging Face
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
Discover Gemini 4 Argon for robotics: leading the ERQA benchmark with physical reasoning, zero-shot control, Real2Sim, and agentic workflows.
Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. The post Offloaded inference for real-world physical AI robotics appeared first on Microsoft Research.
A Blog post by Amazon on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
