Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection
cs.CV
Submitted: 2026-10-06
Updated: 2026-10-06
Sources
- Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
- AlignGemini: Generalizable AI-Generated Image Detection Through Task-Model Alignment
- Steering CLIP's vision transformer with sparse autoencoders
- ICA Lens: Interpreting Language Models Without Training Another Dictionary
- OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detection
- Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- A Benchmark Dataset for MLLM-Generated Image Detection: GPT Image2 & Nano Banana2
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models