ViRA is introduced, a planner-agnostic visual representation alignment framework that keeps the planner architecture and inference cost unchanged and develops ViRA-Diffusion, a diffusion-based planner trained without auxiliary perception supervision, which achieves 92.3 EPDMS on NAVSIM v2 navtest.
Zi-Hao Zhang, Hao-Chen Tian, Tianyu Li et al.· 1 citation
Omni LLMs can naturally locate key audio and visual evidence and integrate information across modalities for audiovisual reasoning. Existing audio-visual reasoning benchmarks that mainly rely on multiple-choice questions usually score models solely based on answer correctness, making it difficult to assess whether a mo...
Xiao-Xing Hu, Wen-Xi Yao, Chao-Yuan Shi et al.· 0 citations
Driving world action models (WAMs) learn from paired trajectories and future observations. Post-training with reinforcement learning allows the policy to explore alternative trajectories and improve planning using driving rewards. However, driving logs contain future videos only for the recorded trajectories, leaving t...
Chang-Hui Jing, Hao-Chen Tian, Hong-Chen Li et al.· 1 citation
V-ICAL is introduced, a novel benchmark designed to evaluate video-based ICL for multimodal agents that seamlessly connects in-context knowledge induction with core agentic capabilities, including state grounding, temporal memory, planning, and adaptation in dynamic environments.
Zi-Qian Fan, Shi-Bo Xu, Jun-Jie Li et al.· 0 citations
Contact-rich dexterous manipulation requires policies that translate physical feedback into motion commands while regulating interaction loads across evolving multi-contact interactions. This requires haptic observations of contact state and action supervision showing how commands should adapt. Existing policies often...
Nai-Sheng Ye, Yin-Zhe Zhou, Jun-Kai Zhao et al.· 0 citations
Bench2Dex is meant as a platform for studying visuo-tactile learning across dexterous hands and offers a shared setting for algorithm development while tactile hardware and simulation models are still evolving.
Zhen-Jie Yang, Yi-Deng Zhang, Dong-Jie Zhang et al.· 1 citation
This work introduces MINT (Minting IN-the-Wild Trajectories), a foundation model for world-space hand motion reconstruction from ego-centric RGB video and develops an open-source labeling EGOPIPELINE that converts large collections of public egocentric videos into structured camera-and-hand trajectory supervision.
Zi-Jie Zhu, Wei-Ren Cai, Yi-Zhou Wang et al.· 3 citations
HandEdit serves as a critical resource at the intersection of image editing and robotics: it advances embodiment-aware editing models while enabling scalable dexterous robotic learning from abundant human video data, paving the way for more generalizable Embodied AI.
Zhen-Jie Yang, Xingyu Jiao, Guopeng Zhong et al.· 5 citations
WorldScape Policy 2.0 is introduced, a controllable WAM with reasoning-augmented long short-term memory and fine-grained instruction following and in-context adaptation that demonstrates superior capabilities in long-horizon autonomous planning, fine-grained instruction following and in-context adaptation.
Hai-Sheng Su, Zong-Dai Liu, Xin Jin et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.