arXiv AI

ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision

ZoomGain introduces a data construction pipeline that exploits the global-to-zoom perception gap to generate fine‑grained visual questions. By creating questions from full‑image context and verifying answers only on zoomed‑in views, the method ensures unambiguous, language‑prior‑free queries and high‑quality distractors for multiple‑choice tasks. Using this pipeline, the authors built ZoomGainBench, a 1,000‑question bilingual benchmark, and demonstrated that training on 9 K ZoomGain samples markedly boosts the visual perception abilities of 4B/9B VLMs, surpassing many larger models on perception benchmarks.

arXiv Machine Learning
Jun 15

Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes

arXiv:2602. 00593v4 Announce Type: replace-cross Abstract: Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation.

By Yifan Jiang, Cong Zhang, Bofei Zhang, Qiaofeng Zheng, Yifan Yang, Bingzhang Wang, Yew-Soon Ong
arXiv AI
Oct 28

Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception

The paper introduces EvidenceConnect, a data‑synthesis framework that generates training examples by zooming into related image regions to create questions requiring comparison, aggregation, or chaining of visual evidence. By retaining only reference answers agreed upon by independent vision‑language models and discarding questions that survive region ablation, the authors train base VLMs with RLVR to produce Zooming without Zooming v2 (ZwZ2). Although the synthesized data are not benchmark‑specific, ZwZ2 shows improvements across fine‑grained and spatial perception, embodied spatial reasoning, multimodal long‑context understanding, multimodal agent tasks, and general visual reasoning, demonstrating that strengthening the shared capability of connecting evidence yields more generalizable multimodal perception.

By Lai Wei, Yatai Li, Liangbo He, Jun Lan, Renjie Gu, Linhan Cao, Junkai Lin, Huijia Zhu, Weiqiang Wang, Linghe Kong, Yue Wang, Zhuosheng Zhang, Weiran Huang
arXiv Computer Vision
Aug 28

Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information

The paper introduces Visual Retrieval Heads (VRHs), a small fraction of attention heads in vision‑language models that are causally responsible for grounding text descriptions to image regions. By recasting head‑scoring methods and evaluating across eleven VLMs and five benchmarks, the authors show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect. VRHs generalize across various visual reference tasks, preserve output format while corrupting localization, and transfer causally across models sharing an LLM backbone.

By Chanho Park, Daehyeon Choi, Jihyun Lee, Minhyuk Sung
arXiv AI
Oct 15

PixSearch: Region-Grounded Retrieval for Knowledgeable Large Multimodal Models

arXiv:2601.19060v2 Announce Type: replace-cross Abstract: Multimodal Retrieval-Augmented Generation (MM-RAG) augments visual question answering (VQA) with external knowledge, but many systems rely on...

By Jeonghwan Kim, Renjie Tao, Sanat Sharma, Jiaqi Wang, Kai Sun, Zhaojiang Lin, Seungwhan Moon, Lambert Mathias, Anuj Kumar, Heng Ji, Xin Luna Dong