Omni‑Diffusion‑Distill is a two‑stage distillation framework that compresses unified multimodal diffusion large language models (dLLMs) into a single efficient student while preserving both image generation and multimodal understanding. In the first stage the student learns to skip decoding steps by replaying cached teacher trajectories, and in the second stage it is refined on intermediate states along its own rollouts. The method introduces a pairwise collision penalty to reduce repetition in parallel text decoding and entropy‑matched guidance to prevent entropy collapse in image generation, achieving state‑of‑the‑art trade‑offs: reducing image generation from 128 to 8 steps and multimodal understanding from 512 to 64 steps, yielding 18.2× and 21.2× wall‑clock speedups and strong performance on GenEval, DPG‑Bench, MM‑Vet, and COCO captioning.
By Hong Huang, Chenhongyi Yang, Junzhe Sun, Animesh Sinha, Wuyang Chen, Yifan Jiang
arXiv:2604. 16514v5 Announce Type: replace-cross Abstract: Autoregressive vision-language models (VLMs) deliver strong multimodal capability, but their token-by-token decoding imposes a fundamental inference bottleneck.
By Baoyou Chen, Hanchen Xia, Peng Tu, Haojun Shi, Liwei Zhang, Yuxuan Yao, Weihao Yuan, Siyu Zhu
arXiv:2602.10216v2 Announce Type: replace
Abstract: A single text prompt passed to a diffusion model yields a wide range of visual outputs determined solely by a stochastic process, leaving users wit...
By Pawe{\l} Skier\'s, Emilia Kaczmarczyk, Tomasz Trzci\'nski, Kamil Deja
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:2603. 28762v2 Announce Type: replace-cross Abstract: Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt.
By Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or
arXiv:2608. 01035v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential autoregressive decoding.
By Zhihao Zhu, Hanlin Shang, Mingwang Xu, Feipeng Cai, Zhuolin He, Yaoyi Li, Jianhua Han, Hang Xu, Siyu Zhu
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
arXiv:2605. 13974v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood.
By Evelyn Turri, Davide Bucciarelli, Sara Sarto, Lorenzo Baraldi, Marcella Cornia
arXiv:2606. 15796v1 Announce Type: cross Abstract: Mechanistic interpretability seeks to explain neural network behavior by decomposing model computations into interpretable features and circuits.
By Artyom Mazur, Nina Konovalova, Aibek Alanov
arXiv:2610.33062v1 Announce Type: cross
Abstract: Unified large multimodal models (ULMMs) are able to perform visual reasoning through interleaved text-image generation, but generating explicit inter...
By Jaeyong Ko, Hankyeol Kim, Pilsung Kang
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-...
VIVAS is a new Vision‑Language Model pre‑training framework that addresses the lack of fine‑grained visual perception in existing VLMs. It introduces a unified token space and a dense‑structural‑semantic vision tokenizer that expands the textual vocabulary with visual tokens, enabling vision‑language unified autoregressive supervision over both visual details and linguistic content. Trained on 12.4 T tokens, VIVAS achieves state‑of‑the‑art results on 7 tasks and 39 multimodal benchmarks.
By Zhehan Kan, Yubo Zhu, Xinghua Jiang, Zhixiang Wei, Shifeng Liu, Wei Tong, Sheng Zhong, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun