Author

Jiaxin Li

h-index 0 View on Semantic Scholar

We have 3 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation

Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordinated subtasks. Existing world-action models (WAMs) jointly predict short-horizon visual futures and actions, but typically lack explicit subtask-level reasoning. We pro...

Shu-Kai Gong, Xuan-Ran Zhai, Yintianrun Zhang et al. · 0 citations

#artificial intelligence Jun 2026

HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration

HAT-4D is proposed, the first agentic framework designed to reconstruct the 3D geometry, temporal dynamics, and physical interactions of multiple objects from a single video, accompanied by a novel multi-dimensional evaluation protocol focused on physical plausibility and temporal consistency.

Jia-Xin Li, Yu-Xiang Wu, Zhenkai Zhang et al. · arXiv.org · 0 citations

Preprint Aug 2026

Population-Scalable Multi-Agent World Modeling

Kora is proposed, a scalable multi-agent world model that supports inference-time expansion to arbitrary numbers of agents without retraining and decouples world-state evolution from visual rendering and introduces a population-agnostic rendering mechanism for incorporating other agent information.

Renjie Zhao, Yu-Xiang Wu, Mingyu Zhang et al. · 1 citation