← Back to all news
arXiv Computer Vision By Chanho Park, Daehyeon Choi, Jihyun Lee, Minhyuk Sung

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

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Aug 20

ReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models

ReWEIGH the Evidence is a training‑free decoding technique that calibrates token‑level ordinal visual evidence to reduce hallucinations in large vision‑language models. It aggregates vocabulary ranks across visual positions, compares candidates to a token‑specific reference derived from unlabeled images, and applies a bounded penalty only when evidence falls below this reference. Experiments on four 7B backbones show up to a 21.3% reduction in hallucinated object mentions while largely preserving or improving descriptive and general performance, with minimal added latency.

By Jihae Jeong, Junha Choi, Hwanjo Yu
llmsmultimodalsafety
More like this →
Hugging Face Trending Papers
Aug 13

Dual-Stream Cross-Anchor Correction Grounding Long-Form Captions and the Domain Limits of Object-Level Anchors

Object hallucination in multimodal large language models arises when language priors and corpus co-occurrence bias outweigh the visual evidence, with nothing tying an individual object mention to what the image shows. Most remedies intervene at decoding time without training, yet under a unified protocol their benefit is confined to short captions;supervised fine-tuning (SFT) on a detail- rich corpus lengthens captions, but over forty percent still name absent objects.

llmsfine-tuningmultimodalbenchmarkssafety
More like this →
Hugging Face Trending Papers
Jul 23

CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA

Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression understanding, visual grounding, object recognition, knowledge retrieval, and reasoning-yet existing benchmarks typically report only end-task accuracy, obscuring where failures arise.

llmsragnlpmultimodalbenchmarks
More like this →
arXiv AI
Jun 24

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

arXiv:2605. 08245v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input.

By Harshvardhan Saini, Samyak Jha, Yiming Tang, Dianbo Liu
llmsragagentsfine-tuningmultimodalbenchmarkssafety
More like this →