arXiv Computer Vision
Latent Watermarks under Generative Editing: A Benchmark and Analysis of Detection Survival
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jul 7
Evaluating and Understanding Model Editing for Medical Vision Language Models
arXiv:2607. 05310v1 Announce Type: new Abstract: Model editing promises a fast, targeted way to correct post-deployment mistakes in medical vision-language models (VLMs) without costly retraining.
arXiv AI
Jun 30
Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
arXiv:2511. 05852v4 Announce Type: replace-cross Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs).
arXiv AI
Jul 24
PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing
arXiv:2607. 21318v1 Announce Type: cross Abstract: Replacing an object with one that differs in category or shape requires complete source removal, natural target formation unconstrained by the source silhouette, and preservation of unrelated content.
arXiv Computer Vision
Oct 2
Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation
arXiv:2610.01670v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly used as automated judges for instruction-based image editing and as reward signals for model...
Hugging Face Trending Papers
Jul 23
PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing
Replacing an object with one that differs in category or shape requires complete source removal, natural target formation unconstrained by the source silhouette, and preservation of unrelated content. Existing training-free editors either localize edits from terminal predictions under source and target prompts or preserve unrelated content through spatially unselective source-feature reuse without explicit region discovery.
arXiv Computation and Language
Oct 1
Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes
arXiv:2609.38722v1 Announce Type: cross Abstract: LLM watermarking has become an effective approach to distinguishing AI-generated text from human-written text by embedding detectable patterns during...