JW
Junxin Wang
cs.CVcs.AI
On Valency
published · living versionsW_af3g4cpf·v1 · currentpublished
PEAR: Adaptive Advantage Reshaping for Perception and Exploration in Large Vision-Language Models
with Yingfeng Luo, Xiangchen Song, Weiqiao Shan, Runsong Zhao +10
1 version
Preprints & journals
2 papers in the corpus · 2026Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models2603.16253v2 · Junxin Wang, Dai Guan, Weijie Qiu et al.2026 · 0 citationsarXiv
Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward Models2603.16600v2 · Weijie Qiu, Dai Guan, Junxin Wang et al.2026 · 0 citationsarXiv
Career total: 2 works. 2 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.