ReLATE: Learning Relative Representations for Post-Hoc Multimodal Alignment
cs.CV, cs.AI, cs.LG
Submitted: 2026-05-16
Updated: 2026-11-01
Terminology
Sources
- Linearly Mapping from Image to Text Space
- CoCa: Contrastive Captioners are Image-Text Foundation Models
- PaLI: A Jointly-Scaled Multilingual Language-Image Model
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