JL

Jianwei Lv

cs.AIcs.CLcs.CV

On Valency

published · living versions

W_qufrgsry·v1 · currentpublished

Reinforcement Learning with Visually Attributable On-Policy Self-Distillation

with Shiao Xie, Siyu Chen, Xiandong Li, Yujin Wang

1 version

Preprints & journals

8 papers in the corpus · 2025–2026

Reinforcement Learning with Visually Attributable On-Policy Self-Distillation2610.26856v1 · Shiao Xie, Siyu Chen, Jianwei Lv et al.2026 · 0 citationsarXivon Valency

EGSD: Event-Grounded Self-Distillation for Streaming Video Understanding2609.36803v3 · Yuwei Miao, Xuesheng Zhang, Wenhao Zou et al.2026 · 0 citationsarXiv

G-CARL: Grounded Checklist-Aligned Reward Learning for Patient-Oriented Medical Report Interpretation2608.20331v1 · Shiao Xie, Siyu Chen, Jianwei Lv et al.2026 · 0 citationsarXiv

MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents2607.18999v2 · Guofeng Zhang, Yizeng Quan, Huaiyi Fang et al.2026 · 0 citationsarXiv

PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus2606.08938v1 · Gen Li, Yuanze Hu, Zhichao Yang et al.2026 · 0 citationsarXiv

EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA2605.27846v1 · Yunsheng Zeng, Gen Li, Yuwei Miao et al.2026 · 0 citationsarXiv

C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning2605.27860v3 · Yuwei Miao, Gen Li, Yunsheng Zeng et al.2026 · 0 citationsarXiv

ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference2510.02361v2 · Haojie Ouyang, Jianwei Lv, Lei Ren et al.2025 · 0 citationsarXiv

Career total: 10 works. 8 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.