arXiv AI October 31, 2026 By Nanxiang Jiang, Yang Liu, Yuanhao Wang, Min Xu

Localizing Concepts in Visual Autoregressive Models

The paper introduces LoCo, a model-agnostic framework that localizes where and when specific concepts appear in visual autoregressive models across Layer, Scale, and Position dimensions. It also presents LoCoBench, a dataset covering ten categories, and demonstrates the method on models such as Infinity, HunyuanImage-3.0, and InfinityStar. Using these localizations, the authors apply concept erasure, model personalization, and adversarial concept injection, achieving state‑of‑the‑art performance with reduced computational cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 25

Concept Removal for Frontier Image Generative Models

arXiv:2606. 25548v1 Announce Type: cross Abstract: Image generative models are trained on massive, largely uncurated internet-scale datasets that contain undesirable visual concepts.

By Aditya Kumar, Pierre Joly, Adam Dziedzic, Franziska Boenisch

diffusion benchmarks safety

arXiv Computer Vision

Sep 28

C2P-VAR: Continual and Compositional Personalization in Visual Autoregressive Models

arXiv:2605.19750v2 Announce Type: replace Abstract: Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation, yet their personalization capabilit...

By Junhao Li, Xinhao Zhong, Yi sun, Yuxia Qiao, Bin Chen, Shu-Tao Xia, Yaowei Wang

diffusion safety

arXiv Computer Vision

Aug 26

Representation Learning in Diffusion and Flow-based Model: An Application Aspect

The article surveys how diffusion and flow-based generative models learn rich visual representations and how these representations can be used to improve generation and other perception tasks. It introduces a three-tier framework that categorizes work into improving generative quality via representation learning, extracting representations for perception, and developing unified applications. The survey covers downstream tasks such as image classification, dense prediction, instance-level perception, and annotation-scarce scenarios, offering a taxonomy and highlighting future research directions.

By Yanchen Xu, Sida Huang, Zhenyu Gu, Ruishu Zhu, Yilan Gao, Hongyuan Zhang

diffusion computer-vision

Hugging Face Trending Papers

Aug 25

Representation Learning in Diffusion and Flow-based Model: An Application Aspect

Diffusion models and flow-based models have recently become the dominant paradigms in generative modeling, largely due to their ability to learn rich, multi-level visual representations through large-...

diffusion computer-vision

arXiv AI

Jul 1

Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

arXiv:2606. 31699v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points.

By Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed, Marco Grangetto, Stephan Alaniz

rag diffusion robotics safety

arXiv Computer Vision

Sep 30

Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models

arXiv:2609.37537v1 Announce Type: new Abstract: Machine unlearning has emerged as a critical post-hoc safety measure to erase sensitive concepts from Text-to-Image (T2I) models without prohibitive re...

By Arian Komaei Koma, Seyed Amir Kasaei, Aida Aryafar, Matin Ghiasi, Ali Aghayari, Amirhossein Souri, Mohammad Mosayyebi, AmirMahdi Sadeghzadeh, Mohammad Hossein Rohban

diffusion benchmarks safety

One email a morning, machine-written

Related stories

Concept Removal for Frontier Image Generative Models

C2P-VAR: Continual and Compositional Personalization in Visual Autoregressive Models

Representation Learning in Diffusion and Flow-based Model: An Application Aspect

Representation Learning in Diffusion and Flow-based Model: An Application Aspect

Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models