Ming Zhang
konglongge
·
AI & ML interests
LLMs
Recent Activity
authored a paper about 10 hours ago
DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training authored a paper about 10 hours ago
SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents authored a paper about 10 hours ago
AI Can Learn Scientific TasteOrganizations
Update README.md
#1 opened 13 days ago
by konglongge