Simulation enables large-scale, low-cost robot data generation, but policies trained in simulation often fail to transfer to the real world due to the sim-to-real visual discrepancies. Existing approaches often rely on intermediate representations, which can discard rich semantic information or require additional perce...
Huang Huang, Wen-Si Ai, Zi-Yu Chen et al.· 0 citations
World-action models (WAMs) couple future prediction with robot control, yet existing systems often vary the video backbone, interaction structure, supervision, and inference procedure simultaneously, making their design choices difficult to compare. We introduce OPENWAM, an open world-action modeling framework built ar...
Heng Yu, David Yuan, Ju-Ze Zhang et al.· 0 citations
Teleoperated demonstrations are a primary source of data for robot manipulation, and teleoperated interventions are a primary mechanism for correcting policies at deployment. Yet most teleoperation systems close the loop through vision alone and are built around parallel-jaw grippers, limiting both what the robot can e...
Zhan-Peng He, Joaquin Palacios, Zhang-Yu Wang et al.· 0 citations
Human videos offer a scalable source of demonstrations for dexterous robot manipulation. However, existing human-to-simulation-to-robot (Human2Sim2Robot) pipelines rely on predefined procedures that struggle to accommodate diverse object properties and interactions, particularly those involving articulated and deformab...
You-Hui Wang, Yun-Zhu Li, Fei-Fei Li et al.· 0 citations
Memory-dependent robotic manipulation requires policies to use information that is no longer available in the current observation. Retaining history alone is insufficient: memory must preserve information that supports future actions. One challenge is whether a memory-free foundation model can learn to retain and use h...
Yi-Ze Liu, Huang Huang, Yi-Ning Hong et al.· 0 citations
A robot may lose sight of an object it must later retrieve, need to recall what a person demonstrated earlier, or track which steps of a task it has already completed. Current vision-language-action (VLA) policies often fail once the information needed for action disappears from the current observation, making memory c...
Yi-Ze Liu, Ke Wang, Mac Schwager et al.· 0 citations
A concept-centric framework for building agents that can learn continually and reason flexibly across multiple domains and offers several advantages, including data efficiency, compositional generalization, continual learning, and zero-shot transfer.
Jia-Yuan Mao, Joshua B. Tenenbaum, Jia-Jun Wu· Communications of the ACM· 14 citations· ⚡1
InSight is a framework for self-guided skill acquisition that uses a VLM to identify primitives missing from a VLA's repertoire, grounds the VLM's proposals through robot execution, and distills new primitives from successful rollouts into the VLA.
M. Wang, Lars W. Osterberg, Stephen Tian et al.· arXiv.org· 3 citations· ⚡1
Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LOTAPO , a self-generated process-supervision method based on backward leave-one-turn attribution. For each search turn, LOTA...
This work introduces MindTopo, a benchmark of topological intuition across five properties grounded in cognitive science and formal topology: continuity, separation, order, enclosure, and knots, which performs better on reasoning than on planning, and the best-performing model remains far below observed human performan...
Yun-Fei Ge, An-Bang Liu, Qineng Wang et al.· 0 citations
DemoMimic (Dexterous Motion Mimic), a policy that manipulates objects by focusing on their geometry local to the contact points to improve sim-to-real consistency, yielding a single real-world policy that transfers across objects of varying shape, scale, mass, and friction wherever local contact structure is preserved.
TrAct is proposed, a world-model-based robot decision-making framework that uses visual tracks as an intermediate interface between control and prediction, enabling more accurate world modeling and stronger robot generalization.
Zhi-Hang Cao, Howard Ji, Kevin Zhang et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
