4 papers
VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
Jiahe Feng
GRPO-style reinforcement learning has advanced vision-language reasoning, but its sequence-level rewards provide limited credit assignment for individual reasoning tokens. On-polic…
Discrete Double-Bracket Flows for Isotropic-Noise Invariant Eigendecomposition
ZhiMing Li, JiaHe Feng
We study eigendecomposition on under streaming observations , where the isotropic background may be time-varying and arbit…
TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration
Ye Li, Jiahe Feng, Yuan Meng +10
Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. Existing diffusion model…
DoPI: Doctor-like Proactive Interrogation LLM for Traditional Chinese Medicine
Zewen Sun, Ruoxiang Huang, Jiahe Feng +7
Enhancing interrogation capabilities in Traditional Chinese Medicine (TCM) diagnosis through multi-turn dialogues and knowledge graphs presents a significant challenge for modern A…