English
Related papers

Related papers: Bridging the Discrete-Continuous Gap: Unified Mult…

200 papers

Multimodal large language models (MLLMs) extend the success of language models to visual understanding, and recent efforts have sought to build unified MLLMs that support both understanding and generation. However, constructing such models…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Hanyu Wang , Jiaming Han , Ziyan Yang , Qi Zhao , Shanchuan Lin , Xiangyu Yue , Abhinav Shrivastava , Zhenheng Yang , Hao Chen

Classical methods in robot motion planning, such as sampling-based and optimization-based methods, often struggle with scalability towards higher-dimensional state spaces and complex environments. Diffusion models, known for their…

Robotics · Computer Science 2026-03-20 Edward Sandra , Lander Vanroye , Dries Dirckx , Ruben Cartuyvels , Jan Swevers , Wilm Decré

The burgeoning field of camouflaged object detection (COD) seeks to identify objects that blend into their surroundings. Despite the impressive performance of recent models, we have identified a limitation in their robustness, where…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Xue-Jing Luo , Shuo Wang , Zongwei Wu , Christos Sakaridis , Yun Cheng , Deng-Ping Fan , Luc Van Gool

Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within their teacher's domain. Thus, fast and high-quality generation…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Yara Bahram , Mélodie Desbos , Mohammadhadi Shateri , Eric Granger

Vocal-to-accompaniment (V2A) generation, which aims to transform a raw vocal recording into a fully arranged accompaniment, inherently requires jointly addressing an accompaniment trilemma: preserving acoustic authenticity, maintaining…

Sound · Computer Science 2026-04-14 Qi Wang , Zhexu Shen , Meng Chen , Guoxin Yu , Chaoxu Pang , Weifeng Zhao , Wenjiang Zhou

Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion models as a standalone component for perception tasks, employing…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Shuhong Zheng , Zhipeng Bao , Ruoyu Zhao , Martial Hebert , Yu-Xiong Wang

Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion…

Computation and Language · Computer Science 2026-05-11 Georgios Batzolis , Mark Girolami , Luca Ambrogioni

Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. To support wider…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Runhui Huang , Kaixin Cai , Jianhua Han , Xiaodan Liang , Renjing Pei , Guansong Lu , Songcen Xu , Wei Zhang , Hang Xu

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

Generating 3D human motion from text descriptions remains challenging due to the diverse and complex nature of human motion. While existing methods excel within the training distribution, they often struggle with out-of-distribution…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Zongye Zhang , Bohan Kong , Qingjie Liu , Yunhong Wang

Generative modeling is typically framed as learning mapping rules, but from an observer's perspective without access to these rules, the task becomes disentangling the geometric support from the probability distribution. We propose that…

Machine Learning · Statistics 2025-12-04 Rui Tong

Text-to-Motion (T2M) generation aims to synthesize realistic and semantically aligned human motion sequences from natural language descriptions. However, current approaches face dual challenges: Generative models (e.g., diffusion models)…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Zhengdao Li , Siheng Wang , Zeyu Zhang , Hao Tang

Current SMILES-based diffusion models for molecule generation typically support only unimodal constraint. They inject conditioning signals at the start of the training process and require retraining a new model from scratch whenever the…

Machine Learning · Computer Science 2025-08-21 Yunzhe Zhang , Yifei Wang , Khanh Vinh Nguyen , Pengyu Hong

Masked diffusion models (MDMs) have achieved notable progress in modeling discrete data, while their potential in molecular generation remains underexplored. In this work, we explore their potential and introduce the surprising result that…

Machine Learning · Computer Science 2025-09-29 Hyunjin Seo , Taewon Kim , Sihyun Yu , SungSoo Ahn

We present an novel framework for efficiently and effectively extending the powerful continuous diffusion processes to discrete modeling. Previous approaches have suffered from the discrepancy between discrete data and continuous modeling.…

Machine Learning · Computer Science 2024-10-31 Yuxuan Gu , Xiaocheng Feng , Lei Huang , Yingsheng Wu , Zekun Zhou , Weihong Zhong , Kun Zhu , Bing Qin

Masked Diffusion Models (MDMs) have emerged as a powerful generative modeling technique. Despite their remarkable results, they typically suffer from slow inference with several steps. In this paper, we propose Di$\mathtt{[M]}$O, a novel…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Yuanzhi Zhu , Xi Wang , Stéphane Lathuilière , Vicky Kalogeiton

Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffer from a critical reliability gap: as sequences grow,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Haoyu Chen , Qing Liu , Yuqian Zhou , He Zhang , Zhaowen Wang , Mengwei Ren , Jingjing Ren , Xiang Wang , Zhe Lin , Lei Zhu

This work presents a forward-only diffusion (FoD) approach for generative modelling. In contrast to traditional diffusion models that rely on a coupled forward-backward diffusion scheme, FoD directly learns data generation through a single…

Machine Learning · Computer Science 2025-09-29 Ziwei Luo , Fredrik K. Gustafsson , Jens Sjölund , Thomas B. Schön

With the emergence of diffusion models as a frontline generative model, many researchers have proposed molecule generation techniques with conditional diffusion models. However, the unavoidable discreteness of a molecule makes it difficult…

Machine Learning · Computer Science 2025-06-05 Jinho Chang , Jong Chul Ye

Augmentation for dense prediction typically relies on either sample mixing or generative synthesis. Mixing improves robustness but misaligned masks yield soft label ambiguity. Diffusion synthesis increases apparent diversity but, when…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Pengyu Jie , Wanquan Liu , Rui He , Yihui Wen , Deyu Meng , Chenqiang Gao