agi-hackathon

AI & ML interests

None defined yet.

Recent Activity

wanng  authored a paper about 10 hours ago

WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts

wanng  authored a paper about 11 hours ago

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

xianbao  submitted a paper 3 months ago

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

View all activity

Team members 9