3 papers
cs.CY2026
Contemporary AI lacks the imagination to diverge or negate in science
Honglin Bao, Siyang Wu, Xiao Liu +3
Bold claims that AI will accelerate scientific discovery have raced ahead of evidence from working scientists, yet large-scale, scientist-in-the-loop evidence is scarce. Here we mo…
cs.CV2026
InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
Xinxin Liu, Shiwei Gan, Xiao Liu +3
Video Large Language Models (Video-LLMs) achieve strong performance in video understanding, but their excessive visual tokens bring substantial computational overhead. Existing tra…
cs.CV2026
ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding
Xiao Liu, Nayu Liu, Junnan Zhu +6
Video understanding requires active evidence seeking, motivating tool-augmented video agents for temporal reasoning, cross-modal understanding, and complex question answering. Exis…