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
The paper demonstrates that vision‑language models (VLMs) possess a small set of attention heads, called Visual Retrieval Heads (VRHs), that are causally responsible for linking text prompts to specific image regions. By adapting head‑scoring techniques from language models, the authors identify VRHs as the heads whose attention from output prediction tokens, summed over the ground‑truth referent region, most reliably indicates causal grounding. Experiments across eleven VLMs and five referring‑expression benchmarks show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect, and that VRHs generalize across diverse visual tasks and transfer across models sharing an LLM backbone.
Abundant visual information strengthens vision-language model (VLM) perception, yet massive visual tokens raise inference costs. Existing visual token pruning methods rely on similarity-based guidance, which exploits pairwise text-vision and vision-vision token correlations for compression.
arXiv:2607. 26107v1 Announce Type: cross Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions.
By Xinran Liu, Shouqian Shi, Yutong Chen, Ge Wang, Xin-Wei Yao, Sheng Zhong
arXiv:2608. 04496v1 Announce Type: cross Abstract: Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottleneck for efficient inference.
By Chen Zhong, Xiao An, Zijie Wang, Jiepan Li, Guangyi Yang, Wei He
arXiv:2606. 06890v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence.
By Runyu Zhou, Qi Zhang, Qixun Wang, Yisen Wang
arXiv:2608.22429v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
By Changjiang Jiang, Qiannian Zhao, Lei Xin, Jinxiang Xie, Preslav Nakov, Zhuohan Xie
The paper introduces RVSD, a training‑free, plug‑and‑play decoding framework that combines token sparsification with Semantic‑Space Visual Retrieval (SSVR) to reduce visual hallucinations in large vision‑language models. RVSD employs a semantics‑directed token selection strategy to prune redundant tokens while preserving essential visual information, and uses SSVR to perform on‑demand cross‑modal retrieval within a shared semantic space. Experiments show that RVSD achieves state‑of‑the‑art performance in mitigating visual hallucinations while maintaining strong suppression in long‑context generation.
By Canjie Liu, Jiawen Kang, Jinbo Wen, Zishao Zhong
FOVEA introduces a cache‑friendly, on‑demand visual evidence adaptation for multimodal speculative decoding, enabling a lightweight draft model to dynamically retrieve a bounded subset of visual memory based on a cumulative‑mass rule. The retrieved visual readout is fused with the draft hidden state via a lightweight gated residual correction, avoiding the insertion of visual tokens into the autoregressive context. Experiments on various vision‑language backbones and benchmarks show that FOVEA improves draft acceptance and speeds up end‑to‑end decoding by up to 2.13× compared to traditional autoregressive decoding.
By Hengjie Zhu, Dayan Wu, Zihao Zhang, Xinze Liu, Jingxuan Yu, Peng Fu, Zheng Lin, Weiping Wang, Ding Wang
Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features can discard text, local attributes, and spatial relationships, while high-resolution inputs substantially increase context length and inference latency.
arXiv:2608.21762v1 Announce Type: cross
Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image...
By Jinchang Zhu, Rong Fu, Yi Ding, Chenghao Wu, Ying Liu, Menglin Yang
arXiv:2609.07937v1 Announce Type: cross
Abstract: Structured visual reasoning, such as image puzzles, demands fine-grained visual perception, an ability current Vision Language Models (VLMs) lack. VL...
By Harsha Patnala, Debopriyo Banerjee, Ayush Sunil Munot, Somak Aditya