Scaling Reward Modeling without Human Supervision
Paper • 2603.02225 • Published
Jingxuan Fan
fjxdaisy
AI & ML interests
None yet
Recent Activity
updated a dataset about 2 months ago
fjxdaisy/ssrm_700k published a dataset about 2 months ago
fjxdaisy/ssrm_700k updated a dataset 2 months ago
fjxdaisy/Skywork-Reward-Preference-80K-v0.2Organizations
authored 5
papers 3 months ago
HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics
Paper • 2410.09988 • Published
Humanity's Last Exam
Paper • 2501.14249 • Published • 77
User-Assistant Bias in LLMs
Paper • 2508.15815 • Published
Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMs
Paper • 2510.09885 • Published