Zhaoxiang Zhang
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.
The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.
The paper presents World Pilot, a Vision-Language-Action framework that augments VLA models with priors from a World-Action Model to improve performance on manipulation tasks.
Papers
World Pilot: Steering Vision-Language-Action Models with World-Action Priors
Zefu Lin, Rongxu Cui, Junjia Xu, Xiaojuan Jin +3 more
The paper presents World Pilot, a Vision-Language-Action framework that augments VLA models with priors from a World-Action Model to improve performance on manipulation tasks.