Beyond Modality Preference: Controlling Multimodal Arbitration under Modality Conflict in MLLMs
cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
- LLaVA-OneVision: Easy Visual Task Transfer
- A Survey on Benchmarks of Multimodal Large Language Models
- Challenges in Understanding Modality Conflict in Vision-Language Models
- Evaluating and Steering Modality Preferences in Multimodal Large Language Model
- When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs
- Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
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