This collection is used to store series of models on the project Reinforcement Learning for Reflection Ability of Math Reasoning Model.
SII-BoHuang
SII-BoHuang
AI & ML interests
SII is an institution dedicated to innovation in education and research in the field of AI. Bo Huang is part of SII, focusing on LLM Agent.
Recent Activity
upvoted a paper 4 days ago
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs upvoted a paper 16 days ago
MMSkills: Towards Multimodal Skills for General Visual Agents upvoted a paper about 1 month ago
Hybrid Policy Distillation for LLMsOrganizations
None yet
models 19
SII-BoHuang/verl_new_ORZ_verl_4_3_global_step_425
Updated
SII-BoHuang/verl_new_ORZ_verl_4_3_global_step_400
Updated
SII-BoHuang/verl_new_ORZ_verl_4_3_global_step_150
Updated
SII-BoHuang/verl_new_ORZ_verl_4_3_global_step_175
Updated
SII-BoHuang/verl_new_ORZ_verl_4_3_global_step_375
Updated
SII-BoHuang/test_ORZ_Qwen_2_5_7b_step_1_Actor
Updated • 7
SII-BoHuang/ORZ_Qwen_2_5_7b_step_90_Critic_exp330
Updated
SII-BoHuang/ORZ_Qwen_2_5_7b_step_90_Actor_exp330
Updated
SII-BoHuang/ORZ_Qwen_2_5_7b_step_90_Crtic_exp330
Updated
SII-BoHuang/ORZ_Qwen_2_5_7b_step_60_Crtic_exp330
Updated