Xiangyan Liu
xyliu6
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents upvoted a paper about 1 month ago
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows upvoted a paper 4 months ago
Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward ModelOrganizations
None yet
datasets 14
xyliu6/DSTVD-backup
Updated • 5
xyliu6/k12-freeform-extended
Viewer • Updated • 15.4k • 104 • 1
xyliu6/geometry3k
Viewer • Updated • 3k • 593
xyliu6/noisyrollout_evaluation_data
Updated • 9
xyliu6/deita_6k_processed_cs5260
Viewer • Updated • 8.53k • 12
xyliu6/k12-freeform
Viewer • Updated • 10.2k • 347 • 2
xyliu6/mathverse_vision_dominant
Viewer • Updated • 788 • 46 • 1
xyliu6/mathverse_text_only_black
Viewer • Updated • 788 • 44
xyliu6/ursa_r1_random_10k
Viewer • Updated • 9.76k • 30
xyliu6/mathverse_text_only
Viewer • Updated • 788 • 43