English
Related papers

Related papers: AlignTok: Aligning Visual Foundation Encoders to T…

200 papers

Recent advances in text-to-image diffusion models have enabled the generation of diverse and high-quality images. While impressive, the images often fall short of depicting subtle details and are susceptible to errors due to ambiguity in…

Computer Vision and Pattern Recognition · Computer Science 2025-01-13 Idan Schwartz , Vésteinn Snæbjarnarson , Hila Chefer , Ryan Cotterell , Serge Belongie , Lior Wolf , Sagie Benaim

Recent contrastive multimodal vision-language models like CLIP have demonstrated robust open-world semantic understanding, becoming the standard image backbones for vision-language applications. However, recent findings suggest high…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Mayug Maniparambil , Raiymbek Akshulakov , Yasser Abdelaziz Dahou Djilali , Sanath Narayan , Ankit Singh , Noel E. O'Connor

Latent diffusion models excel at generating high-quality images but lose the benefits of end-to-end modeling. They discard information during image encoding, require a separately trained decoder, and model an auxiliary distribution to the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Alan Baade , Eric Ryan Chan , Kyle Sargent , Changan Chen , Justin Johnson , Ehsan Adeli , Li Fei-Fei

Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compared to continuous video representation. Previous discrete…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Yupeng Zhou , Zhen Li , Ziheng Ouyang , Yuming Chen , Ruoyi Du , Daquan Zhou , Bin Fu , Yihao Liu , Peng Gao , Ming-Ming Cheng , Qibin Hou

In this paper, we explore the possibility of building a unified foundation model that can be adapted to both vision-only and text-only tasks. Starting from BERT and ViT, we design a unified transformer consisting of modality-specific…

Computer Vision and Pattern Recognition · Computer Science 2021-12-15 Qing Li , Boqing Gong , Yin Cui , Dan Kondratyuk , Xianzhi Du , Ming-Hsuan Yang , Matthew Brown

Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Xinliang Zhang , Lei Zhu , Hangzhou He , Shuang Zeng , Ourui Fu , Jiakui Hu , Zhengjian Yao , Yanye Lu

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Hyun Lee , Hyemin Jeong , Yejin Kim , Hyungwook Choi , Hyunsoo Cho , Soo Kyung Kim , Joonseok Lee

Efficient tokenization of videos remains a challenge in training vision models that can process long videos. One promising direction is to develop a tokenizer that can encode long video clips, as it would enable the tokenizer to leverage…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Huiwon Jang , Sihyun Yu , Jinwoo Shin , Pieter Abbeel , Younggyo Seo

Tokenizer, serving as a translator to map the intricate visual data into a compact latent space, lies at the core of visual generative models. Based on the finding that existing tokenizers are tailored to image or video inputs, this paper…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Junke Wang , Yi Jiang , Zehuan Yuan , Binyue Peng , Zuxuan Wu , Yu-Gang Jiang

Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not…

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Jihao Liu , Jinliang Zheng , Boxiao Liu , Yu Liu , Hongsheng Li

In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network. A challenging problem as such results in unwelcome complexity increase and inferior…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-16 Haici Yang , Inseon Jang , Minje Kim

The rapid success of Vision Large Language Models (VLLMs) often depends on the high-resolution images with abundant visual tokens, which hinders training and deployment efficiency. Current training-free visual token compression methods…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Jianjian Li , Junquan Fan , Feng Tang , Gang Huang , Shitao Zhu , Songlin Liu , Nian Xie , Wulong Liu , Yong Liao

Diffusion-based methods represented as stochastic differential equations on a continuous-time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score matching, which can…

Machine Learning · Computer Science 2024-11-05 Sarthak Mittal , Korbinian Abstreiter , Stefan Bauer , Bernhard Schölkopf , Arash Mehrjou

Recent advances in diffusion transformers (DiTs) have enabled promising single-turn image editing capabilities. However, multi-turn editing often leads to progressive semantic drift and quality degradation.In this work, we study this…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Xiaoce Wang , Sifan Zhou , Kaifei Wang , Leli Xu , Xuerui Qiu , Tao He , Ming Li

Audio tokenizers are fundamental to unifying audio understanding and generation. Understanding requires high-level semantics, while generation demands semantic and acoustic details. Existing unified tokenizers jointly encode both in…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-28 Zhisheng Zhang , Xiang Li , Yixuan Zhou , Jing Peng , Guoyang Zeng , Zhiyong Wu

We present a framework for adapting a large pretrained latent diffusion model to high-resolution Synthetic Aperture Radar (SAR) image generation. The approach enables controllable synthesis and the creation of rare or out-of-distribution…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Solène Debuysère , Nicolas Trouvé , Nathan Letheule , Olivier Lévêque , Elise Colin

A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers…

Machine Learning · Computer Science 2022-11-16 Rafael Pastrana

We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. Different from existing paradigms that directly synthesize a full image from a single input (e.g., a latent code), the new…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Yanhong Zeng , Huan Yang , Hongyang Chao , Jianbo Wang , Jianlong Fu

Image quantization is a crucial technique in image generation, aimed at learning a codebook that encodes an image into a discrete token sequence. Recent advancements have seen researchers exploring learning multi-modal codebook (i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Guotao Liang , Baoquan Zhang , Zhiyuan Wen , Junteng Zhao , Yunming Ye , Kola Ye , Yao He
‹ Prev 1 8 9 10 Next ›