From Pixels to Prompts: Physics-Guided Language Enhancement for AI-Generated Image Detection
cs.CV
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- Gemini: A Family of Highly Capable Multimodal Models
- Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges
- Detecting GAN generated Fake Images using Co-occurrence Matrices
- Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
- Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
- ClipCap: CLIP Prefix for Image Captioning
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