English
Related papers

Related papers: Lavida-O: Elastic Large Masked Diffusion Models fo…

200 papers

End-to-end autonomous driving systems built on Vision Language Models (VLMs) have shown significant promise, yet their reliance on autoregressive architectures introduces some limitations for real-world applications. The sequential,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Can Cui , Yupeng Zhou , Juntong Peng , Sung-Yeon Park , Zichong Yang , Prashanth Sankaranarayanan , Jiaru Zhang , Ruqi Zhang , Ziran Wang

We present Dynin-Omni, the first masked-diffusion-based omnimodal foundation model that unifies text, image, and speech understanding and generation, together with video understanding, within a single architecture. Unlike autoregressive…

Computation and Language · Computer Science 2026-04-02 Jaeik Kim , Woojin Kim , Jihwan Hong , Yejoon Lee , Sieun Hyeon , Mintaek Lim , Yunseok Han , Dogeun Kim , Hoeun Lee , Hyunggeun Kim , Jaeyoung Do

Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality and generation speed. MDMs denoise by progressively…

Machine Learning · Computer Science 2026-04-15 Tianyu Xie , Shuchen Xue , Zijin Feng , Tianyang Hu , Jiacheng Sun , Zhenguo Li , Cheng Zhang

Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fragmented architectures, cascaded pipelines, and misaligned…

This paper introduces TBAC-UniImage, a novel unified model for multimodal understanding and generation. We achieve this by deeply integrating a pre-trained Diffusion Model, acting as a generative ladder, with a Multimodal Large Language…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Junzhe Xu , Yuyang Yin , Xi Chen

We propose MAViD, a novel Multimodal framework for Audio-Visual Dialogue understanding and generation. Existing approaches primarily focus on non-interactive systems and are limited to producing constrained and unnatural human speech. The…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Youxin Pang , Jiajun Liu , Lingfeng Tan , Yong Zhang , Feng Gao , Xiang Deng , Zhuoliang Kang , Xiaoming Wei , Yebin Liu

Existing text-to-image diffusion models primarily generate images from text prompts. However, the inherent conciseness of textual descriptions poses challenges in faithfully synthesizing images with intricate details, such as specific…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Wei Li , Xue Xu , Jiachen Liu , Xinyan Xiao

In this paper, we propose a novel framework for controllable video diffusion, OmniVDiff , aiming to synthesize and comprehend multiple video visual content in a single diffusion model. To achieve this, OmniVDiff treats all video visual…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Dianbing Xi , Jiepeng Wang , Yuanzhi Liang , Xi Qiu , Yuchi Huo , Rui Wang , Chi Zhang , Xuelong Li

Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Shanghua Gao , Pan Zhou , Ming-Ming Cheng , Shuicheng Yan

Multimodal variational autoencoders have demonstrated their ability to learn the relationships between different modalities by mapping them into a latent representation. Their design and capacity to perform any-to-any conditional and…

Machine Learning · Computer Science 2025-02-04 Daniel Wesego , Pedram Rooshenas

Object-centric learning aims to represent visual data with a set of object entities (a.k.a. slots), providing structured representations that enable systematic generalization. Leveraging advanced architectures like Transformers, recent…

Computer Vision and Pattern Recognition · Computer Science 2023-09-25 Ziyi Wu , Jingyu Hu , Wuyue Lu , Igor Gilitschenski , Animesh Garg

Open-Vocabulary Object Detection (OVOD) aims to enable detectors to generalize across categories by leveraging semantic information. Although existing methods are pretrained on large vision-language datasets, their inference is still…

Artificial Intelligence · Computer Science 2026-04-21 Chujie Wang , Jianyu Lu , Zhiyuan Luo , Xi Chen , Chu He

Diffusion models are the de facto approach for generating high-quality images and videos, but learning high-dimensional models remains a formidable task due to computational and optimization challenges. Existing methods often resort to…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Jiatao Gu , Shuangfei Zhai , Yizhe Zhang , Josh Susskind , Navdeep Jaitly

Recent progress in unified models for image understanding and generation has been impressive, yet most approaches remain limited to single-modal generation conditioned on multiple modalities. In this paper, we present Mogao, a unified…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Chao Liao , Liyang Liu , Xun Wang , Zhengxiong Luo , Xinyu Zhang , Wenliang Zhao , Jie Wu , Liang Li , Zhi Tian , Weilin Huang

We introduce M-VADER: a diffusion model (DM) for image generation where the output can be specified using arbitrary combinations of images and text. We show how M-VADER enables the generation of images specified using combinations of image…

Diffusion models have shown incredible capabilities as generative models; indeed, they power the current state-of-the-art models on text-conditioned image generation such as Imagen and DALL-E 2. In this work we review, demystify, and unify…

Machine Learning · Computer Science 2022-08-26 Calvin Luo

Talking head generation with arbitrary identities and speech audio remains a crucial problem in the realm of the virtual metaverse. Recently, diffusion models have become a popular generative technique in this field with their strong…

Graphics · Computer Science 2025-08-11 Xinyang Li , Gen Li , Zhihui Lin , Yichen Qian , GongXin Yao , Weinan Jia , Aowen Wang , Weihua Chen , Fan Wang

Vision-based motion capture solutions often struggle with occlusions, which result in the loss of critical joint information and hinder accurate 3D motion reconstruction. Other wearable alternatives also suffer from noisy or unstable data,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Junkun Jiang , Jie Chen , Ho Yin Au , Jingyu Xiang

Large Language Models (LLMs) have significantly advanced molecular discovery, but existing multimodal molecular architectures fundamentally rely on autoregressive (AR) backbones. This strict left-to-right inductive bias is sub-optimal for…

Artificial Intelligence · Computer Science 2026-04-08 Seohyeon Shin , HanJun Choi , Jun-Hyung Park , Hong Kook Kim , Mansu Kim

Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs. Previous approaches augment textual dialogues with retrieved images,…

Computation and Language · Computer Science 2024-10-04 Hossein Aboutalebi , Hwanjun Song , Yusheng Xie , Arshit Gupta , Justin Sun , Hang Su , Igor Shalyminov , Nikolaos Pappas , Siffi Singh , Saab Mansour