Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models
cs.CV, cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/MR-Sherif/JPTA
Terminology
Sources
- DataComp: In search of the next generation of multimodal datasets
- Fine-Grained Visual Classification of Aircraft
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Tent: Fully Test-time Adaptation by Entropy Minimization
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