This work proposes a self-supervised Track-Any-Point approach that learns from unlabeled surgical videos by establishing global pixel correspondences and inferring point trajectories through contrastive random walks, and achieves performance comparable to existing semi-supervised approaches while implicitly handling ti...
Jiaming Zhang, Zi-Jian Wu, Mehran Armand et al.· Proceedings of the Hamlyn Sy...· 0 citations
Value-Guided Flow Matching (VGFM), a scalable offline RL framework that enables dense value-guided shaping within a flow-based policy while avoiding BPTT and additional algorithmic overhead, is proposed.
Vision-language-action (VLA) deployment can reduce inference latency while changing closed-loop task behavior while changing closed-loop task behavior through deployment evaluation, and deployment evaluation should jointly report latency, artifact inspection, interface constraints, and closed-loop success.
A runtime mechanism that grows and prunes the heads of the attention block during reinforcement learning, governed by two signals: the effective rank of the on-policy context distribution, which triggers growth when representational capacity becomes insufficient, and the per-head output magnitude, which flags redundant...
G. Cirrincione, Adriano Fagiolini· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Three robotic art installations which explore the aesthetics of adaptive behavior use learning and evolutionary processes not as a means to optimize a specific solution, but as an aesthetic experience on its own, suggesting new modes of interdisciplinary art-science research.
GroundBench is introduced, a diagnostic benchmark that separates explanations through six branch-and-merge conditions, each adding a controlled information bundle, and a counterfactual re-ask targeting a real alternate part visible in the same image.
Diffusion learning leverages the statistical mechanism of diffusion processes for learning, reasoning, and inferring complex distributions from data. Recent advances in diffusion learning have been transformative, with robot learning emerging as a key opportunity area, with applications spanning perception, control, an...
Max Muchen Sun, Cem Bilaloglu, Ananya Rao et al.· 0 citations
Comprehensive benchmarks demonstrate that GzDRL achieves the highest workstation throughput among the evaluated frameworks while remaining competitive with GPU-accelerated simulators on laptop hardware, and maintains precise agent-environment synchronization, multi-agent scalability, and experiment-level reproducibilit...
Amaldev Haridevan, Kan Junjie, Jinjun Shan· 0 citations
Benchmarks agree that vision-language models reason poorly about low-level manipulation, but an aggregate accuracy score does not say which step fails. We separate two steps that affordance questions conflate: identifying which part of an object to act on, and knowing what action that part requires. Across 19 articulat...
The rapid expansion of operational satellites and orbital debris has increased the frequency of close approach events in low Earth orbit (LEO), creating a higher operational burden for satellite operators. This problem is especially critical for satellites using electric propulsion, where low-thrust maneuver capability...
DART-VLN is presented, a training-free inference-time framework that combines Test-Time Memory Decay, which reweights stale and redundant memory slots without modifying their stored content, with Anti-Loop Regularization, a lightweight next-hop penalty that discourages immediate reversals.
Shaoheng Zhang, Zhi-Cheng Li, Guang-Fu Ma et al.· arXiv.org· 0 citations
It is found that Humans and VLMs diverge in their responses -- though this is modulated by the type of questions asked, and that Humans answer similarly independent of where they are from (Lima/NYC), and that Humans answer similarly independent of where they are from (Lima/NYC).
A. Cespedes, Marcelo Chincha, Dunant Cusipuma et al.· arXiv.org· 0 citations
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.
Gemini Robotics ER 2 helps robots reason, collaborate, and solve real-world tasks. It represents a step change in video understanding, tool orchestration, and multi-robot collaboration for robotic applications.
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
