Is Forgetting Unified? Exploring Concept Unlearning in Unified Multimodal Models
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
- Emerging Properties in Unified Multimodal Pretraining
- EAR: Erasing Concepts from Unified Autoregressive Models
- ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
- Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation
- Erased or Dormant? Rethinking Concept Erasure Through Reversibility
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