Early successes on agentic robotics point to a potential paradigm shift toward using coding agents to control robots. Existing robotics benchmarks are built around visuomotor policy learning, leaving it open whether coding agents can reliably control diverse robots under physical-world constraints. We therefore introdu...
Kang-Rui Wang, Qineng Wang, Chang-He Chen et al.· 0 citations
AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in isolation against static targets. Real cyber operations, however, are dynamic and coupled: security postures constantly change as attackers and defenders ada...
Bangya Liu, Jianhong Tu, Yu-Jing Pan et al.· 0 citations
For large language models (LLMs) and multimodal large language models (MLLMs), model-reported self-confidence is often miscalibrated, yet it may still be useful for efficient evaluation. At the same time, LLM-as-a-judge offers a scalable alternative to direct human auditing, but its practical benefit depends on calibra...
Harine Choi, Chen-Chen Kuai, Zi-Hao Li et al.· 0 citations
Real-world Vision-Language Navigation (VLN) requires agents to act under partial observability, where map structure, semantic cues, and target locations may be incomplete or incorrectly inferred by foundation models. This paper presents a lightweight, training-free, and uncertainty-aware framework for cooperative multi...
Fan Pu, Keshu Wu, Ji-Wan Jiang et al.· 0 citations
CyberArena is a dynamic, symmetric adversarial benchmark built around multi-round attack-and-defense combat, and introduces a dynamical model that maps match dynamics into unified, multidimensional scores across offensive, defensive, and domain-specific capabilities.
Bangya Liu, Jianhong Tu, Yu-Jing Pan et al.· 0 citations
Contextual Credit Policy Optimization weights observation-matched peers from other trajectories by contextual similarity, computed from frozen LLM representations and accumulated trajectory statistics, allowing peers from similar contexts to contribute more to a step's baseline.
Hui-Wen Han, Zi-Yao Zeng, Zi-Hao Zhu et al.· 0 citations
How should demonstration quality be used during vision-language-action (VLA) pretraining to improve performance after target-task fine-tuning? We compare weighting, filtering, and conditioning across reward definitions and label granularities using 5,000 naturally suboptimal human demonstrations and 24 target tasks. Wi...
Ming-Xuan Yan, Li-Tian Gong, Di Huang et al.· 0 citations
MEVA (Mesh-Enhanced Volumetric Autoencoder), a self-supervised framework that encodes voxel-level image intensity together with cortical mesh geometry, including curvature and cortical thickness at each surface vertex, into one shared set of imaging features, suggests that adding cortical surface geometry to volumetric...
Tian Xia, Nuo Chen, Zi-Hao Zhu et al.· 0 citations
Results show that directly steering internal robot-policy representations can improve the performance of robot policies at inference time and show that directly steering internal robot-policy representations can improve the performance of robot policies at inference time.
Jiu-Zhou Lei, Chang Liu, Da-You Li et al.· 0 citations
3D brain MRI generation has made significant advances in medical imaging, simulation, and controllable anatomical analysis. However, existing generative models typically synthesize 3D volumes monolithically, often overlooking regional anatomical structures and limiting local controllability. To address these limitation...
Hui-Wen Han, Lu Liu, Bangya Liu et al.· 0 citations
Dense 3D reconstruction is critical for clinical endoscopic navigation and documentation. While Gaussian Splatting SLAM systems show promise in this domain, they fundamentally rely on strict multi-view photometric consistency. In routine procedures, this assumption is severely violated by intermittent optical degradati...
This work introduces ENCORE, which gives the agent a few demonstrations as evidence to read rather than as training data, and shows that on RoboDojo tasks whose instructions leave the goal unstated, no program succeeds without demonstrations.
Yi-Fan Kang, Zihan Wang, Zhi-Wen Fan et al.· arXiv.org· 6 citations· ⚡2
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.