VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be rendered, but first-class substrates for problem solving beyond language. Yet progress remains bottlenecked by the lack of scalable training tasks, reliable feedback, and controlled comparisons across generative substrates. In this work, we introduce VBVR-Pro, a closed-loop testbed that makes native visual reasoning through generation trainable, verifiable, optimizable, and experimentally controllable. 1) Task scaling
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 57%Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning - Apple Machine Learning Research →
- LinkedLinked via arxiv author · 85%Wanqi Yin →
“VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning”
- LinkedLinked via arxiv author · 85%Wei Cheng →
“VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning”
- LinkedLinked via arxiv author · 85%Oscar Qian →
“VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning”
- LinkedLinked via arxiv author · 85%Ziqi Huang →
“VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning”
- LinkedLinked via arxiv author · 85%Haiwen Diao →
“VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning”
- LinkedLinked via arxiv author · 85%Liang Pan →
“VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning”
- LinkedLinked via arxiv author · 85%Haobo Li →
“VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning”