arxiv:2503.00784
Kai Lv (SII)
KaiLv
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? upvoted a paper about 1 year ago
Reasoning or Memorization? Unreliable Results of Reinforcement Learning
Due to Data Contamination upvoted a paper about 1 year ago
Pre-Trained Policy Discriminators are General Reward ModelsOrganizations
None yet
datasets 35
KaiLv/UDR_Go
Viewer • Updated • 283k • 86
KaiLv/UDR_Yelp
Viewer • Updated • 38k • 68
KaiLv/UDR_Yahoo
Viewer • Updated • 37.2k • 131
KaiLv/UDR_WikiAuto
Viewer • Updated • 584k • 47
KaiLv/UDR_TREC
Viewer • Updated • 10.9k • 39
KaiLv/UDR_Subj
Viewer • Updated • 15k • 50
KaiLv/UDR_SST-5
Viewer • Updated • 15.7k • 40
KaiLv/UDR_SST-2
Viewer • Updated • 13.7k • 42
KaiLv/UDR_SNLI
Viewer • Updated • 238k • 59
KaiLv/UDR_SMCalFlow
Viewer • Updated • 73.1k • 52