Xiangyan Liu
xyliu6
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models upvoted a paper 1 day ago
Rethinking the Divergence Regularization in LLM RL upvoted a paper about 1 month ago
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker AgentsOrganizations
None yet
datasets 14
xyliu6/DSTVD-backup
Updated • 4
xyliu6/k12-freeform-extended
Viewer • Updated • 15.4k • 67 • 1
xyliu6/geometry3k
Viewer • Updated • 3k • 406
xyliu6/noisyrollout_evaluation_data
Updated • 6
xyliu6/deita_6k_processed_cs5260
Viewer • Updated • 8.53k • 11
xyliu6/k12-freeform
Viewer • Updated • 10.2k • 252 • 2
xyliu6/mathverse_vision_dominant
Viewer • Updated • 788 • 46 • 1
xyliu6/mathverse_text_only_black
Viewer • Updated • 788 • 20
xyliu6/ursa_r1_random_10k
Viewer • Updated • 9.76k • 17
xyliu6/mathverse_text_only
Viewer • Updated • 788 • 40