arXiv Computer Vision October 1, 2026 By Cong Wei, Xuanchi Ren, Bryan Chu, Weiming Ren, Huan Ling, Jiahui Huang, Laura Leal-Taix\'e, Sanja Fidler, Wenhu Chen, Zian Wang, Jay Zhangjie Wu

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Read the original on arXiv Computer Vision →

PixelUMM is an encoder‑free model that unifies image and video understanding and generation directly in pixel space. It represents images as spatial patches and videos as spatiotemporal tubelets, feeding both through single‑layer linear projections into a shared multimodal backbone. The Mixture‑of‑Transformers architecture blends shared attention with task‑specific parameters, enabling autoregressive text prediction, pixel‑space flow matching, and clean‑pixel video generation, and experiments show competitive performance across tasks while providing design insights for future pixel‑space multimodal models.

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 Computer Vision.

arXiv AI

Aug 11

UniSpace: Unified Visual Representation and Scalable Multimodal Modeling

arXiv:2608. 08676v1 Announce Type: cross Abstract: Semantic vision encoders have become a central visual interface for multimodal understanding and semantic conditioning in image generation.

By Jinbo Yan, Limeng Qiao, Jie Qin, Junyan He, Feize Wu, Guanglu Wan

llms rag diffusion multimodal

arXiv AI

Jun 12

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

arXiv:2606. 13289v1 Announce Type: cross Abstract: Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space.

By Guozhen Zhang, Xuerui Qiu, Yutao Cui, Tianhui Song, Changlin Li, Junzhe Li, Tao Huang, Xiao Zhang, Yang Li, Jianbing Wu, Miles Yang, Zhao Zhong, Liefeng Bo, Limin Wang

llms rag diffusion computer-vision nlp multimodal

arXiv AI

Jun 26

Semantic Generative Tuning for Unified Multimodal Models

arXiv:2605. 18714v2 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.

By Songsong Yu, Yuxin Chen, Ying Shan, Yanwei Li

computer-vision multimodal benchmarks

arXiv AI

Jul 13

M4V: Multimodal Mamba for Efficient Text-to-Video Generation

arXiv:2506. 10915v2 Announce Type: replace-cross Abstract: Text-to-video generation has significantly enriched content creation and holds the potential to evolve into powerful world simulators.

By Jiancheng Huang, Gengwei Zhang, Zequn Jie, Siyu Jiao, Yinlong Qian, Ling Chen, Yunchao Wei, Lin Ma

llms diffusion multimodal benchmarks

arXiv Computer Vision

Sep 24

UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm

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.

By Zhehan Kan, Xinghua Jiang, Yubo Zhu, Yanlin Liu, Xiaochen Yang, Zhixiang Wei, Shifeng Liu, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun

llms efficiency multimodal

Hugging Face Trending Papers

Jul 7

From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models

Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets.

diffusion computer-vision fine-tuning benchmarks

One email a morning, machine-written

Related stories

UniSpace: Unified Visual Representation and Scalable Multimodal Modeling

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

Semantic Generative Tuning for Unified Multimodal Models

M4V: Multimodal Mamba for Efficient Text-to-Video Generation

UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm

From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models