3 papers
cs.CV2026
ReWorld: Learning Better Representations for World Action Models
Tianze Xia, Lijun Zhou, Kaixin Xiong +9
World Action Models (WAMs) model future environment evolution under action conditioning, offering a scalable paradigm for autonomous driving. However, existing approaches focus lar…
cs.CV2026
Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning
Yu Zhu, Yongkang Li, Wenjie Zhu +5
Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (SFT), which often limits reas…
cs.CV2026
Unlocking Positive Transfer in Incrementally Learning Surgical Instruments: A Self-reflection Hierarchical Prompt Framework
Yu Zhu, Kang Li, Zheng Li +1
To continuously enhance model adaptability in surgical video scene parsing, recent studies incrementally update it to progressively learn to segment an increasing number of surgica…