VISTA is a gradient‑based test‑time alignment framework designed for next‑scale visual autoregressive (VAR) image generation. It optimizes intermediate representations within the frozen transformer to enforce compositional constraints, without altering model weights or requiring extra training. Experiments on two benchmarks and two model scales show that VISTA improves compositional accuracy by up to 20% on a 2B backbone and 6% on an 8B backbone, while preserving image quality and enabling a smaller model to outperform a larger one.
By Hossein Shahabadi, Niki Sepasian, Mahdieh Soleymani Baghshah
Visual autoregressive (VAR) models have emerged as a fast, high-quality alternative to diffusion for text-to-image generation, but like diffusion models they exhibit persistent compositional failures,...
arXiv:2607. 00371v1 Announce Type: cross Abstract: Visual AutoRegressive modeling (VAR) has pioneered a coarse-to-fine multi-scale autoregressive generative paradigm, demonstrating strong capabilities in image generation.
By Nuoyan Zhou, Zhijun Tu, Lei Yu, Kun Cheng, Jie Hu, Nannan Wang, Xinghao Chen
arXiv:2609.36661v1 Announce Type: new
Abstract: Visual reprogramming is a parameter-efficient method for adapting pretrained models, yet its training can remain computationally expensive: even with a...
By Zizhao Li, Mohammed Yaqoob Ansari, Xinyu Su, Jiayang Ao, Joseph West, Kourosh Khoshelham
arXiv:2609.37969v1 Announce Type: new
Abstract: High-resolution video generation is expensive, as its cost grows rapidly with the number of spatiotemporal tokens. A practical alternative first genera...
By Haozhe Liu, Tian Ye, Shuchen Xue, Yitong Li, Junsong Chen, Haopeng Li, Jincheng Yu, Duomin Wang, Ruihua Zhang, Lei Zhu, Song Han, Enze Xie
Modern computer vision pipelines remain fragmented, with tasks such as text-to-image generation, editing, restoration, and classical perception handled by separate models. We study Unified Visual Generation (UVG), where a single model produces diverse image-valued outputs through a unified multimodal interface.
arXiv:2510. 19496v3 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks.
By Moshe Kimhi, Nimrod Shabtay, Raja Giryes, Chaim Baskin, Eli Schwartz
arXiv:2608.29904v1 Announce Type: new
Abstract: Modern video generators routinely fail at physical dynamics: objects float, trajectories violate gravity, contacts vanish. Standard denoising and flow-...
By Hai Nguyen-Truong, Tuan-Anh Vu, Dang Huynh
PRISM is a training‑free framework that efficiently selects visual instruction data for multimodal large language models by addressing the anisotropy in visual feature distributions, which causes a Global Semantic Drift. By implicitly re‑centering visual semantics, PRISM removes the influence of global background features, cutting data‑selection and model‑tuning time to 30% of conventional pipelines while improving performance across eight multimodal and three language benchmarks, achieving a 101.7% relative gain over baseline models.
By Jinhe Bi, Aniri, Zengjie Jin, Yifan Wang, Danqi Yan, Wenke Huang, Xiaowen Ma, Sikuan Yan, Artur Hecker, Mang Ye, Xun Xiao, Hinrich Schuetze, Volker Tresp, Yunpu Ma
arXiv:2609.24510v2 Announce Type: replace
Abstract: Recent advances in vision foundation models (VFMs) have shown remarkable capabilities across diverse unimodal visual tasks. However, adapting VFMs...
By Xiaoqiang Lu, Licheng Jiao, Lingling Li, Yuting Yang, Long Sun, Wenping Ma, Xu Liu, Fang Liu
FlashAR is a lightweight post‑training adaptation framework that converts a pre‑trained raster‑scan autoregressive image model into a highly parallel generator using two‑way next‑token prediction. It preserves the original training objective by keeping the horizontal head for row‑wise prediction and adding a lightweight vertical head for column‑wise prediction, with a learnable fusion gate to combine the two predictions. A two‑stage adaptation pipeline—first initializing the vertical head from the pre‑trained model and then jointly fine‑tuning—yields up to a 22.9× speedup for 512×512 image generation while using only 0.05% of the original training data.
By Junkang Zhou, Yefei He, Feng Chen, Weijie Wang, Bohan Zhuang
FAVE (Foveated Adaptive Visual Encoding) is a lightweight, variable‑resolution Vision Transformer that encodes user‑selected image regions at high acuity while maintaining the image’s native geometry. In controlled experiments on small‑object ImageNet crops, FAVE outperforms a fixed‑resolution ViT by 9.4 top‑1 points while using 12.7× fewer FLOPs. When added as a local branch to FastVLM, FAVE improves TextVQA by 1.60 points and GQA attribute accuracy by 1.31 points, achieving a 3.3× speedup over SmolVLM2-2.2B with only 16 extra local tokens.
By Amitangshu Mukherjee, Kaushik Roy