arxiv:2602.12395
Ming Li
MingLiiii
AI & ML interests
None yet
Recent Activity
upvoted a paper about 23 hours ago
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers submitted a paper 1 day ago
How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer ReviewOrganizations
models 9
MingLiiii/cherry-alpaca-pre-experienced-7B
Text Generation • Updated • 7
MingLiiii/cherry-wizardlm-filtered-7B
Text Generation • Updated • 8
MingLiiii/cherry-wizardlm-40-percent-7B
Text Generation • Updated • 7
MingLiiii/cherry-wizardlm-30-percent-7B
Text Generation • Updated • 7
MingLiiii/cherry-wizardlm-20-percent-7B
Text Generation • Updated • 9
MingLiiii/cherry-wizardlm-10-percent-7B
Text Generation • Updated • 16
MingLiiii/cherry-alpaca-15-percent-7B
Text Generation • Updated • 7
MingLiiii/cherry-alpaca-10-percent-7B
Text Generation • Updated • 8
MingLiiii/cherry-alpaca-5-percent-7B
Text Generation • Updated • 8
datasets 6
MingLiiii/Layer_Gradient
Preview • Updated • 408
MingLiiii/Wiz70_Analysis_llama2_13b
Viewer • Updated • 280k • 32
MingLiiii/Wiz70_Analysis_llama2_7b
Viewer • Updated • 280k • 52
MingLiiii/Alpaca_Analysis_llama2_13b
Viewer • Updated • 208k • 34
MingLiiii/Alpaca_Analysis_llama2_7b
Viewer • Updated • 208k • 135
MingLiiii/cherry_wizardlm_filtered
Viewer • Updated • 63.7k • 17