Author

Zehui Chen

h-index 11 View on Semantic Scholar

We have 3 of 31 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 Aug 2026

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

Video-DR is introduced, featuring a decoupled perception-exploration pipeline with stage-wise tool unlocking that compels exhaustive cross-frame visual grounding prior to web retrieval, enabling autonomous exploration that breaks the imitation-learning ceiling.

Zhen Fang, Yu Zeng, Wen-Xuan Huang et al. · 1 citation · ⚡1

Jul 2026

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

VideoCoCo, an agentic dual-engine framework in which executable Blender code serves as a process-level chain of thought, demonstrates that executable code provides an effective, controllable, and inspectable intermediate representation for physically consistent video generation.

Haodong Li, Tianfei Ren, Xiaoxiao Ma et al. · arXiv.org · 8 citations

#artificial intelligence Preprint Aug 2026

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

These results establish source-intent preservation and shared executable-state grounding as key principles for scalable terminal-task synthesis as key principles for scalable terminal-task synthesis.

K. Shi, Zun Wang, Qi-Sheng Su et al. · 0 citations