Pixels, Patterns, but No Poetry: To See The World like Humans
Paper • 2507.16863 • Published • 69 •
6
Hongcheng Gao
HongchengGao
AI & ML interests
Trustworthy ML/NLP and LLM.
Recent Activity
updated a dataset 18 days ago
HongchengGao/LoopLatent-Data published a dataset 18 days ago
HongchengGao/LoopLatent-Data upvoted a paper about 2 months ago
OpenWorldLib: A Unified Codebase and Definition of Advanced World ModelsOrganizations
commented a
paper 10 months ago
commented 3
papers about 1 year ago
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
Paper • 2505.11049 • Published • 61 •
5
Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
Paper • 2503.19622 • Published • 31 •
4
Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
Paper • 2503.19622 • Published • 31 •
4