Query-conditioned vision--language models enable fine-grained interpretation by revealing how visual evidence changes with textual queries. However, evidence conditioned on complete descriptions does...
arXiv:2601.06847v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) can generate convincing clinical narratives, yet frequently struggle to visually ground their statements. We po...
arXiv:2608. 08021v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context.
arXiv:2608.29092v1 Announce Type: new Abstract: Large vision-language models (LVLMs) frequently generate content unsupported by visual inputs. Preliminary experiments show that visual evidence is pri...
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.
EviViT is a lightweight attachment for pretrained vision transformers that learns where to focus detail in high‑resolution images. It uses human visual‑search traces to supervise a question‑conditioned evidence density, guiding regional re‑reading and efficient visual token allocation. The method connects regional features to the global scene via a sparse, coordinate‑aware bridge, improving fine‑grained accuracy across nine host models while using fewer tokens than global‑only processing.
arXiv:2609.16795v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved...
arXiv:2608.21796v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning over external knowledge sources beyond the visua...
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.
arXiv:2607. 07179v1 Announce Type: cross Abstract: Document Visual Question Answering (DocVQA) presents a complex multimodal challenge, requiring models to exploit visual, textual, and layout information from documents.
SlideBank is a training‑free framework that turns each whole‑slide image into a persistent, concept‑indexed evidence bank. It performs coarse‑to‑fine exploration to locate informative regions and multi‑scale views, converts them into explicit morphological observations, and anchors pathology signals to the supporting patches and slide coordinates. During inference, questions are routed to relevant signals and evidence scales, and a confidence‑based cross‑level consensus integrates global, regional, and patch evidence, achieving high accuracy on WSI‑VQA and SlideBench‑BCNB while enabling consistent re‑phrasing and reduced inference cost.
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.