This work introduces SurgCoTBench, the first reasoning-focused benchmark in RAS, and proposes SurgRAW, a clinically aligned Chain-of-Thought (CoT) driven agentic workflow for zero-shot multi-task reasoning in surgery, which surpasses mainstream VLMs and agentic systems and outperforms a supervised model.
Chang Han Low, Ziyue Wang, Tianyi Zhang et al.· IEEE Robotics and Automation...· 20 citations· ⚡2
Recent advances in video generation allow robots to learn manipulation trajectories from generated videos. However, these approaches produce purely kinematic trajectories that lack force information, causing failures in contact-rich tasks where appropriate contact forces are essential for success. In this work, we expl...
Guanhua Ji, Tianyu Li, Dayoon Suh et al.· 0 citations
Factory work is a promising early scenario for embodied AI: assigning repetitive manual jobs to robots has clear economic payoff, and a structured station keeps the jobs tractable for current policies. Vision-Language-Action (VLA) models now dominate as the policy paradigm for these robots. The inference latency of VLA...
Kai-Jun Zhou, Zhi-Yang Li, Le Chen et al.· 0 citations
This work introduces physical rank consistency (PRC) to measure how well tokenization preserves local physical distance rankings after reconstruction, and presents ActionPiece, which preserves physical action relationships through joint supervision of representation learning and quantization.
Shijie Lian, Bin Yu, Zhao-Long Shen et al.· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
Experimental results demonstrate the proposed ${M}^2$Tok, a Multi-head Multi-codebook Action Tokenizer designed to minimize reconstruction error and enhance policy performance, achieves superior reconstruction fidelity and significantly boosts the success rate of VLA models.
Chun-Pu Xu, Zhi-Xuan Liang, Yu-Hao Zhang et al.· 0 citations
This article comprehensively analyzes GPAI systems, focusing on their architectural foundations, current applications, and key limitations, and summarizes promising research directions in data-efficient learning, sim-to-real transfer, edge-compatible architectures, and safety frameworks.
Satyam Gaba, Krutiksinh Rana, Siva Sai et al.· IEEE Internet of Things Jour...· 6 citations· ⚡1
While the proposed method outperforms many state-of-the-art competitors, all methods remain below a micro-averaged frame-level AUC threshold of 70% in the most challenging evaluation setup, confirming the difficulty of the proposed benchmark.
Alexandru-Bogdan Dura, Sebastian Balmuş, Radu Tudor Ionescu· 0 citations
This work uses decentralized object-centric control, where each humanoid is assigned a local attachment region on the shared object and learns to realize pickup and transport through gripperless bimanual pinching, which provides a common control abstraction spanning single-robot pickup, cooperative multi-robot transpor...
Bikram Pandit, Mohitvishnu S. Gadde, A. Shrestha et al.· 0 citations
HINT-Plan employs Vision Language Models to anticipate high-level human intentions from third-person image observations, convert them into goal states, and solve joint task-planning problems, and shows the effectiveness of explicitly incorporating inferred human intentions into formal multi-agent task planning for proa...
Yu-Chen Liu, Luigi Palmieri, Lujun Li et al.· 0 citations
CALOS (Control-Affine Lyapunov On-manifold Safety), a runtime safety layer that enforces attitude constraints on a quadrotor without modifying the underlying learning algorithm, accelerates training convergence and improves data efficiency without producing suboptimal policies.
Fabrizio Cesareo, Sebastiano Mengozzi, N. Mimmo et al.· 0 citations
REVERSAL-BENCH is introduced, a benchmark that controls reversibility via a continuous parameter $\rho$ and provides a reset oracle, a ground-truth verification mechanism to test state recoverability across eight manipulation settings in five physics engines and a safety shield that intervenes before irreversible failu...
RiskWorld, a risk-aware world modeling framework for shared occupancy forecasting and selective trajectory replacement, is introduced and within-setting ablations show that RiskWorld achieves lower collision rates than the current-state rescoring baseline, while forecast reuse enables additional candidates to be evalua...
Rong-Xiang Zeng, Lin-Sen Cai, Jia-Fu Zhang 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.
