English
Related papers

Related papers: Reconstruction Alignment Improves Unified Multimod…

200 papers

We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Daniel Zoran , Nikhil Parthasarathy , Yi Yang , Drew A Hudson , Joao Carreira , Andrew Zisserman

This paper works on non-autoregressive automatic speech recognition. A unimodal aggregation (UMA) is proposed to segment and integrate the feature frames that belong to the same text token, and thus to learn better feature representations…

Computation and Language · Computer Science 2024-03-21 Ying Fang , Xiaofei Li

Text-to-image diffusion models have achieved remarkable progress in recent years. However, training models for high-resolution image generation remains challenging, particularly when training data and computational resources are limited. In…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Ruonan Yu , Songhua Liu , Zhenxiong Tan , Xinchao Wang

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Yaqi Zhao , Wang Lin , Zijian Zhang , Miles Yang , Jingyuan Chen , Wentao Zhang , Zhao Zhong , Liefeng Bo

We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and…

Computer Vision and Pattern Recognition · Computer Science 2015-04-15 Andrej Karpathy , Li Fei-Fei

Imaging distributions of radioactive sources plays a substantial role in nuclear medicine as well as in monitoring nuclear waste and its deposit. Coded Aperture Imaging has been proposed as an alternative to parallel or pinhole collimators,…

Medical Physics · Physics 2023-01-12 T. Meißner , V. Rozhkov , J. Hesser , W. Nahm , N. Loew

The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Tiancheng Gu , Kaicheng Yang , Ziyong Feng , Xingjun Wang , Yanzhao Zhang , Dingkun Long , Yingda Chen , Weidong Cai , Jiankang Deng

Meta-learning has recently been an emerging data-efficient learning technique for various medical imaging operations and has helped advance contemporary deep learning models. Furthermore, meta-learning enhances the knowledge generalization…

Image and Video Processing · Electrical Eng. & Systems 2023-07-14 Sriprabha Ramanarayanan , Arun Palla , Keerthi Ram , Mohanasankar Sivaprakasam

We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. This omnivore model can take in any single-modality or multimodal data input indiscriminately (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-09 Quan Sun , Qiying Yu , Yufeng Cui , Fan Zhang , Xiaosong Zhang , Yueze Wang , Hongcheng Gao , Jingjing Liu , Tiejun Huang , Xinlong Wang

Minute-scale cinematic video generation is a central challenge for generative video models. Existing paradigms address only fragments of this challenge: single-shot extrapolation preserves an anchor but lacks cinematic structure, while…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Akide Liu , Jinbo Xing , Chaojie Mao , Ye Li , Zeyu Zhang , Yefei He , Weijie Wang , Zihan Wang , Yu Liu , Gholamreza Haffari , Bohan Zhuang

Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration agents, powered by vision-language models and large…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Jianglin Lu , Yuanwei Wu , Ziyi Zhao , Hongcheng Wang , Felix Jimenez , Abrar Majeedi , Yun Fu

Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to perform edits without extensive model adjustments, offering…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Wenyi Mo , Tianyu Zhang , Yalong Bai , Bing Su , Ji-Rong Wen

Educational illustrations play a central role in communicating abstract concepts, yet current multimodal large language models (MLLMs) remain limited in producing pedagogically coherent and semantically consistent educational visuals. We…

Artificial Intelligence · Computer Science 2025-11-25 Zhenyu Wu , Jian Li , Hua Huang

Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Ruyi Xu , Yuan Yao , Zonghao Guo , Junbo Cui , Zanlin Ni , Chunjiang Ge , Tat-Seng Chua , Zhiyuan Liu , Maosong Sun , Gao Huang

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

All-in-one image restoration seeks to recover clean images from inputs affected by diverse and unknown degradations using a unified framework. Recent methods have shown strong performance by identifying degradation characteristics to guide…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Eunho Lee , Rei Kawakami , Youngbae Hwang

Image feature matching, a foundational task in computer vision, remains challenging for multimodal image applications, often necessitating intricate training on specific datasets. In this paper, we introduce a Unified Feature Matching…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Yide Di , Yun Liao , Hao Zhou , Kaijun Zhu , Qing Duan , Junhui Liu , Mingyu Lu

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Computation and Language · Computer Science 2024-06-18 Zhipeng Chen , Kun Zhou , Wayne Xin Zhao , Junchen Wan , Fuzheng Zhang , Di Zhang , Ji-Rong Wen

Vision-Language-Action (VLA) models show promise in embodied reasoning, yet remain far from true generalists-they often require task-specific fine-tuning, incur high compute costs, and generalize poorly to unseen tasks. We propose MetaVLA,…

Artificial Intelligence · Computer Science 2026-01-29 Chen Li , Zhantao Yang , Han Zhang , Fangyi Chen , Chenchen Zhu , Anudeepsekhar Bolimera , Marios Savvides

Video behavior recognition demands stable and discriminative representations under complex spatiotemporal variations. However, prevailing data augmentation strategies for videos remain largely perturbation-driven, often introducing…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Feng-Qi Cui , Jinyang Huang , Sirui Zhao , Jinglong Guo , Qifan Cai , Xin Yan , Zhi Liu