Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models
cs.CV, cs.CL
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/parkquasar/Image-Retrieval-Heads
Terminology
Sources
- Pixtral 12B
- Qwen3-VL Technical Report
- Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- In-context Learning and Induction Heads
- Representation Learning with Contrastive Predictive Coding
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs