Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only afterwards. Yet manipulation often hinges on precisely the visual signals most vulnerable to this abstraction, e.g., local geometry, boundaries, depth, and subtle st...
Wei-Chen Fan, Hai-Wen Diao, Peng-Hao Wu et al.· 0 citations
This work introduces HarnessEval-W, an agentified evaluation pipeline that brings the harness paradigm from the LLM ecosystem to world model benchmarking, and applies HarnessEval-W to 18 representative world models over 330 evaluation cases.
Wei-Liang Chen, Haowen Sun, Jun Gao et al.· 3 citations
UMM-Reflection is introduced, which applies reinforcement learning (RL) to complete reflection trajectories inside one unified model: sibling trajectories share one initial image, so the group-relative advantage compares reflection strategies, and one trajectory-level advantage updates both the reflection tokens and th...
Yi-Jia Fan, Zi-Qi Huang, Zhongang Cai et al.· 0 citations
The Evaluation Agent framework is proposed, which employs human-like strategies for efficient, dynamic, multi-round evaluations, offering detailed, user-tailored analyses and is efficient, promptable, explainable, and scalable across models and tools.
Shu-Lin Tian, Zi-Qi Huang, Fan Zhang et al.· 2 citations
Apple-PI is introduced, the first benchmark that anchors video-model evaluation explicitly in physical laws, and is positioned as a diagnostic foundation for guiding future video models toward world models with law-grounded physical intelligence.
Runmao Yao, Kairui Hu, Yukang Cao et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.