Permute-then-Adapt: Weak-to-Strong Contrastive Image-Text Adaptation
cs.CV
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/JinhaoLee/Permute-then-Adapt
Terminology
Sources
- Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
- Data Filtering Networks
- Fine-Grained Visual Classification of Aircraft
- EVA-CLIP: Improved Training Techniques for CLIP at Scale
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- FG-CLIP: Fine-Grained Visual and Textual Alignment
- Demystifying CLIP Data
- Florence: A New Foundation Model for Computer Vision
- Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
- Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
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