Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning
cs.CV, cs.AI
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models
- TOFU: A Task of Fictitious Unlearning for LLMs
- MUSE: Machine Unlearning Six-Way Evaluation for Language Models
- Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
- Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
- Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
- DataComp: In search of the next generation of multimodal datasets
- 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