arxiv:2505.02391
Hanning Zhang
HanningZhang
AI & ML interests
None yet
Organizations
models 282
HanningZhang/deepseek_only_conjecture_claude_deepseek_train_data_max1_5e-7_bs32_decay1e-6_2ep_ep1
Text Generation • 7B • Updated • 7
HanningZhang/PhysProver-7B
Text Generation • 7B • Updated • 10 • 1
HanningZhang/physlean_ds_prover_noapply_grpo_1e-6_bs256_step35
Text Generation • 7B • Updated • 14
HanningZhang/physlean_ds_prover_grpo_1e-6_bs256_step90
Text Generation • 7B • Updated • 6
HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_one_sample_ep1
Text Generation • 8B • Updated • 7
HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_one_sample_ep2
Text Generation • 8B • Updated • 9
HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_all_ep2
Text Generation • 8B • Updated • 7
HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_all_ep1
Text Generation • 8B • Updated • 7
HanningZhang/physicslean_kimina_train_gen_from_grok_deepseek_one_sample_ep2
Text Generation • 8B • Updated • 6
HanningZhang/physicslean_kimina_train_gen_from_grok_deepseek_one_sample_ep1
Text Generation • 8B • Updated • 6
datasets 236
HanningZhang/SAGE-all-correct-top_p10_selfcorr
Viewer • Updated • 2.84k • 20
HanningZhang/SAGE-all-correct-top_p10
Viewer • Updated • 2.84k • 19
HanningZhang/SAGE-all-correct
Viewer • Updated • 2.99k • 17
HanningZhang/OpenGenAlign-v2
Viewer • Updated • 43.5k • 61
HanningZhang/RAG-Reward-Modeling-v2
Viewer • Updated • 43.5k • 63
HanningZhang/scalebio_distill_qwen_math
Viewer • Updated • 2k • 19
HanningZhang/test-self-rewarding
Viewer • Updated • 40k • 12
HanningZhang/test-no-self-rewarding
Viewer • Updated • 40k • 21
HanningZhang/MLE-Policy-Trajectory
Viewer • Updated • 1.22k • 16
HanningZhang/MLE-Reward-Rating
Viewer • Updated • 1.86k • 13