Hanning Zhang's picture

11 5

Hanning Zhang

HanningZhang

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

PRL: Process Reward Learning Improves LLMs' Reasoning Ability and Broadens the Reasoning Boundary

updated a model 6 days ago

HanningZhang/deepseek_only_conjecture_claude_deepseek_train_data_max1_5e-7_bs32_decay1e-6_2ep_ep1

published a model 6 days ago

HanningZhang/deepseek_only_conjecture_claude_deepseek_train_data_max1_5e-7_bs32_decay1e-6_2ep_ep1

View all activity

Organizations

Papers 2

arxiv:2505.02391

arxiv:2502.19613

models 282

HanningZhang/deepseek_only_conjecture_claude_deepseek_train_data_max1_5e-7_bs32_decay1e-6_2ep_ep1

Text Generation • 7B • Updated 6 days ago • 76

HanningZhang/physlean_ds_prover_noapply_curri_grpo_1e-6_bs256_step35

Text Generation • 7B • Updated 14 days ago • 77

HanningZhang/physlean_ds_prover_noapply_grpo_1e-6_bs256_step35

Text Generation • 7B • Updated 16 days ago • 14

HanningZhang/physlean_ds_prover_grpo_1e-6_bs256_step90

Text Generation • 7B • Updated 18 days ago • 24

HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_one_sample_ep1

Text Generation • 8B • Updated Dec 14, 2025

HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_one_sample_ep2

Text Generation • 8B • Updated Dec 14, 2025

HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_all_ep2

Text Generation • 8B • Updated Dec 14, 2025

HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_all_ep1

Text Generation • 8B • Updated Dec 14, 2025

HanningZhang/physicslean_kimina_train_gen_from_grok_deepseek_one_sample_ep2

Text Generation • 8B • Updated Dec 14, 2025

HanningZhang/physicslean_kimina_train_gen_from_grok_deepseek_one_sample_ep1

Text Generation • 8B • Updated Dec 14, 2025

View 282 models

datasets 233

HanningZhang/OpenGenAlign-v2

Viewer • Updated Sep 30, 2025 • 43.5k • 11

HanningZhang/RAG-Reward-Modeling-v2

Viewer • Updated Sep 30, 2025 • 43.5k • 14

HanningZhang/scalebio_distill_qwen_math

Viewer • Updated Sep 23, 2025 • 2k • 9

HanningZhang/test-self-rewarding

Viewer • Updated Sep 4, 2025 • 40k • 6

HanningZhang/test-no-self-rewarding

Viewer • Updated Sep 4, 2025 • 40k • 5

HanningZhang/MLE-Policy-Trajectory

Viewer • Updated Jul 8, 2025 • 1.22k • 3

HanningZhang/MLE-Reward-Rating

Viewer • Updated Jul 8, 2025 • 1.86k • 5

HanningZhang/mistral1-selected-baseline

Viewer • Updated May 4, 2025 • 3k • 3

HanningZhang/llama32-selected-baseline

Viewer • Updated May 4, 2025 • 3k • 5

HanningZhang/scalebio_reasoning_think_220k_with_system_and_cot

Viewer • Updated Apr 22, 2025 • 193k • 7

View 233 datasets