Diversity-Incentivized Exploration for Versatile Reasoning
Zican Hu
huzican
AI & ML interests
None yet
Recent Activity
upvoted a paper 19 days ago
Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe upvoted a paper about 1 month ago
Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning updated a model 2 months ago
huzican/unify_sft_tit-ckpt-3000Organizations
models 7
huzican/unify_sft_tit-ckpt-3000
Updated
huzican/Qwen2.5-Math-7B-16k-think
7B • Updated
huzican/Baseline-Entropy-RL-Qwen2.5-Math-7B
7B • Updated • 1
huzican/Baseline-Clip-Higher-Qwen2.5-Math-7B
7B • Updated
huzican/Baseline-Passk-Training-Qwen2.5-Math-7B
7B • Updated • 1
huzican/DIVER-TD-Qwen2.5-Math-7B
7B • Updated • 2 • 1
huzican/DIVER-ED-Qwen2.5-Math-7B
7B • Updated • 1
datasets 10
huzican/multiturn_game_tit
Viewer • Updated • 2.21k • 37
huzican/multiturn_game_tit_gemini
Viewer • Updated • 1.19k • 25
huzican/game_multiturn_less5_singleturn
Viewer • Updated • 3.29k • 26
huzican/multiturn_game
Viewer • Updated • 2.45k • 28
huzican/eval_map_size
Viewer • Updated • 100 • 11
huzican/eval_easy
Viewer • Updated • 100 • 61
huzican/eval_map_size_hard
Viewer • Updated • 100 • 36
huzican/test_game
Viewer • Updated • 10.8k • 204
huzican/DIVER-Test
Viewer • Updated • 6.02k • 15
huzican/DIVER-Training-Openr1-Math-46k
Viewer • Updated • 45.8k • 49 • 1