CAPTOR: text-encoder-free grounding by counting caption co-occurrence over the visual words of a frozen encoder
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Phikon-v2, A large and public feature extractor for biomarker prediction
- PanNuke Dataset Extension, Insights and Baselines
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