TIB: Sample-wise Tempered Information Bottleneck for Multimodal Attribution beyond Alignment Assumption
cs.CV, cs.AI, cs.MM
Submitted: 2026-11-08
Updated: 2026-11-08
Project page: https://qiming-huang.github.io/TIB
Terminology
Sources
- Explainable Multimodal Regression via Information Decomposition
- Rethinking Explainability in the Era of Multimodal AI
- The information bottleneck method
- LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
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