OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning
Paper • 2606.08572 • Published • 9
Ningxin Shen
NingxinShen
AI & ML interests
None yet
Recent Activity
upvoted a paper about 11 hours ago
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning upvoted a paper about 13 hours ago
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation upvoted a paper about 13 hours ago
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent TrajectoriesOrganizations
None yet
upvoted a paper about 11 hours ago
upvoted 4
papers about 13 hours ago
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation
Paper • 2606.02320 • Published • 14
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Paper • 2606.02060 • Published • 53
MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
Paper • 2606.01993 • Published • 14
CoVEBench: Can Video Editing Models Handle Complex Instructions?
Paper • 2606.08415 • Published • 44