3 papers
cs.LG2026
ProactiveBench: Can Streaming Video Models Really Interact Like Humans?
Kaixuan Du, Xin Wan, YuKun Wang +5
Streaming video understanding requires models to process continuous multimodal input while maintaining temporal context. Existing evaluations are predominantly reactive: they query…
cs.CV2026
Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward Models
Weijie Qiu, Dai Guan, Junxin Wang +6
Generative reward models (GRMs) for vision-language models (VLMs) often evaluate outputs via a three-stage pipeline: rubric generation, criterion-based scoring, and a final verdict…
cs.CV2026
Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models
Junxin Wang, Dai Guan, Weijie Qiu +7
Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-time scaling. However, they often funct…