zd21/DeepSeek-TD0-PRM
Updated
TDRM
Learning Smooth Reward Models with Temporal Difference for LLM RL and Inference
-
-
zd21/DeepSeek-TD2-PRM
Updated -
zd21/DeepSeek-ScalarPRM
Updated -
zd21/DeepSeek-ScalarORM
Updated -
zd21/DS-R1-Distill-Qwen-1.5B-TDRM
Updated -
zd21/DS-R1-Distill-Qwen-7.5B-TDRM
Updated -
zd21/Qwen2.5-Math-1.5B-TDRM
Updated -
zd21/Qwen2.5-Math-7B-TDRM
Updated -
zd21/Qwen2.5-0.5B-TDRM
Updated -
zd21/Qwen2.5-1.5B-TDRM
Updated -
zd21/GLM4-9B-0414-TDRM
9B • Updated • 6 -
zd21/GLM-Z1-9B-0414-TDRM
9B • Updated • 7 -
zd21/DeepSeek-TD1-PRM
Updated -
TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference
Paper • 2509.15110 • Published • 1