Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional Understanding
Paper recorded by Signals 4 on 2026-11-03 in cs.CV. Abstract reproduced from arXiv; link to the original below.
Published 2026-11-03 on arXiv · recorded by Signals 4 on 2026-11-04
Category: cs.CV · 计算机视觉 · first seen 2026-11-04
Abstract
Vision-language verifiers judge whether an image faithfully matches a textual description, yet existing training pipelines typically rely on static supervision from stronger external judges or curated hard-negative data. Such supervision requires external generation or annotation, is teacher-bounded, and is difficult to adapt as model failures evolve. We introduce PROVE (Perturb-and-Repair Optimiz
Read on arXiv →
Cite this page: Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional Understanding: the #18 most recent of 710 cs.CV papers we have recorded (as of 2026-11-03). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/perturb-repair-verify-self-play-vision-language-verifiers-for-compositional-unde.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free