arxiv:2509.07945
Yuan Pu
puyuan1996
AI & ML interests
None yet
Recent Activity
authored a paper 10 days ago
LightZero: A Unified Benchmark for Monte Carlo Tree Search in General
Sequential Decision Scenarios authored a paper 10 days ago
SafeWork-R1: Coevolving Safety and Intelligence under the
AI-45$^{\circ}$ Law authored a paper 10 days ago
ReZero: Boosting MCTS-based Algorithms by Backward-view and
Entire-buffer ReanalyzeOrganizations
models 0
None public yet
datasets 11
puyuan1996/knowledge_orm_qwen25vl_72B_20251017
Updated • 8
puyuan1996/value_orm_qwen25vl_7B_20251017
Updated • 4
puyuan1996/safe_orm_qwen25vl_72B_20251017
Updated • 5
puyuan1996/base_model_deepseek_70b_after_sft_20251017
Updated • 4
puyuan1996/7b_ppo_jericho_1p8k_his4_iter_0_45_90_180
Preview • Updated • 4
puyuan1996/orz_0p5b_ppo_150step
Preview • Updated • 6
puyuan1996/junyu_backup20250903
Updated • 6
puyuan1996/unizero_mt_moco_dmc8_concat_task_embed_nlayer8_20250221
Preview • Updated • 5
puyuan1996/unizero_mt_dmc18_concat_task_embed_nlayer8_20250221
Preview • Updated • 4
puyuan1996/unizero_mt_atari8_concat_task_embed_nlayer8_20250221
Preview • Updated • 5