PriCBMs: Multi-granular Concept Bottleneck Vision-Language Models for Visual Privacy Recognition
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/sun2293674491-dotcom/PriCBMs
Project page: https://tribhuvanesh.github.io/vpa
Terminology
Sources
- Qwen2.5-VL Technical Report
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
- Kimi K3: Open Frontier Intelligence
- PEAK: Explainable Privacy Assistant through Automated Knowledge Extraction
- PrivLEX: Detecting legal concepts in images through Vision-Language Models
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