Actuator degradation turns quadruped locomotion into a coordination problem requiring joints to compensate for lost actuation. Prior work suggests that morphology-aware graph policies improve learning and generalization under body perturbations. We ask whether these benefits can be strengthened by explicitly modeling h...
Derek You, Zafir Shamsi, Ke-Qin Wang et al.· 0 citations
Shortcut learning is a prevalent issue in robot learning. The limited diversity of robot demonstration datasets can mislead policies into exploiting spurious correlations between tasks and irrelevant features, such as viewpoint or background. Collecting sufficiently diverse robot demonstrations is costly and inefficien...
Jasper Gerigk, Kenzo Aspuru-Takata, Chin-Hsuan Wu et al.· 0 citations
Long-horizon robotic manipulation is often built by chaining independently trained skills. Although each skill can be reliable in isolation, performance degrades sharply when skills are chained: each downstream skill must start from the state its predecessor leaves behind rather than from its training distribution. We...
Pranav Wagh, Yu Fang, Yue Yang et al.· 0 citations
Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost judges a candidate solely by how close its predicted terminal state lies to the goal, leaving the realizability of the intermediate transitions unchecked--a predicted traje...
Gawon Seo, Dongwon Kim, Suha Kwak· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation. Directly decoding actions from vision-language backbone representations enables low-latency control, whereas textual reasoning, pixel-level subgoals, or world-model evaluation of decoded actions c...
This paper introduces Trust Region Q Adjoint Matching (TRQAM), a stable off-policy fine-tuning algorithm that adaptively controls the path-space KL between the fine-tuned and pretrained policies through projected dual descent, achieving stable off-policy RL.
Yong Dong, Kyungmin Lee, Changyeon Kim et al.· arXiv.org· 6 citations· ⚡3
Embodied video world models typically capture both scene evolution and the robot's behavior, which we refer to as the \emph{world} and the \emph{ego}, respectively. The world and the ego exhibit different underlying dynamics: world prediction relies primarily on visual history and emphasizes scene stability, whereas eg...
Zuyao Lin, Jianhui Zhang, Peidong Jia et al.· 0 citations
We study fine-grained execution-constraint following in vision-language-action (VLA) models. Given an invariant task goal, the policy must follow instruction-specified execution constraints, including interaction targets, motion patterns, spatial relations, and terminal configurations. This setting exposes a limitation...
Gaoge Han, Zhengqing Gao, Ziwen Li et al.· 0 citations
Recent progress in text-conditioned human motion generation has been largely driven by diffusion models trained on large-scale human motion data. Building on this progress, recent methods attempt to transfer such models for character animation and real robot control by applying a Whole-Body Controller (WBC) that conver...
Yangsong Zhang, Anujith Muraleedharan, Rikhat Akizhanov et al.· 0 citations
Vision-Language-Action (VLA) models leveraging the native autoregressive paradigm of Vision-Language Models (VLMs) have demonstrated superior instruction-following and training efficiency. Central to this paradigm is action tokenization, yet its design has primarily focused on reconstruction fidelity, failing to addres...
Zibin Dong, Yicheng Liu, Shiduo Zhang et al.· 0 citations
Multi-agent path finding (MAPF) in large networks is computationally challenging. An approach for MAPF is prioritized planning (PP), in which agents plan sequentially according to their priority. Albeit a computationally efficient approach for MAPF, the solution quality strongly depends on the prioritization. Most prio...
Patrick Scheffe, Julius Kahle, Bassam Alrifaee· 0 citations
Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However, whether planning is causally driven by this reasoning remains a critical but unverified assumption. To investigate this, we build DriveMind,...
Xurui Song, Shuo Huai, JingJing Jiang et al.· 0 citations
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.
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.
