LLM Digest

Story

arxiv_cs_cl · Nov 3, 2026 · paper

Source brief

Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models

arxiv.orgNov 3, 2026
original source linked

In brief

Large vision-language models (LVLMs) can process interleaved text and multiple images in a single context, but how they internally identify the image relevant to a question remains poorly understood. We study this gro...

Feed lens

eval

Read the original at arxiv.org →Open in live feed Read that day’s brief

Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models

Earlier in this thread 4 items

AI evals for agents: what they are and how to write them

DR Pixel: Page-Native Deep Research with Vision-Language Models

GeoGuesser Bench: Benchmarking Vision-Language Agents on Interactive Geolocation

WeSearch: A Unified Model-Centric Retrieval Framework for WeChat Search