Focus Matters: Attention-Value Dynamics for Efficient Hallucination Mitigation in Vision-Language Models
cs.CV, cs.AI, cs.CL
Submitted: 2026-04-04
Updated: 2026-11-07
Project page: https://cvsp-lab.github.io/FocusMatters
Terminology
Sources
- Qwen2.5-VL Technical Report
- Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- LLaMA: Open and Efficient Foundation Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
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