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.
arXiv:2606. 25548v1 Announce Type: cross Abstract: Image generative models are trained on massive, largely uncurated internet-scale datasets that contain undesirable visual concepts.
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...
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.
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-...
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.
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...
arXiv:2605. 00273v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation.
arXiv:2611.06838v1 Announce Type: new Abstract: Autoregressive image generation has recently emerged as a competitive visual generation paradigm, yet its generation order is often predefined or heuri...
arXiv:2608. 00716v1 Announce Type: cross Abstract: Robust detection of generated images is critical to counter the misuse of generative models.
UVU is a vision-language unified autoregressive framework that integrates visual supervision directly into the pre-training stage of multimodal large language models. By using continuous visual encoding and a large-scale iterative hierarchical clustering algorithm to build a pixel-level visual codebook, UVU enables lossless representation of visual inputs and autoregressive generation of pixel-level image tokens alongside textual tokens. This approach synergizes pixel-level visual perception with semantic-level visual understanding, allowing models to internalize visual reconstruction capabilities and improve multimodal understanding performance.
TINA+ is a diffusion-consistent, text‑free inversion attack that probes residual visual knowledge in diffusion models after concept erasure. By using optimization‑based inversion and diffusion‑consistent trajectory regularization, it suppresses spurious trajectories that could falsely indicate retained concepts. Experiments across multiple erasure methods, tasks, and model architectures show that TINA+ reliably recovers erased concepts, revealing that many current techniques only sever text‑image links rather than eliminating underlying visual knowledge.
arXiv:2606. 15819v1 Announce Type: cross Abstract: The rapid progress of visual autoregressive (VAR) models has unlocked a transformative frontier for high-fidelity text-to-image synthesis, while heightening concerns over the safety alignment of generated content.