English
Related papers

Related papers: Adapting Self-Supervised Representations as a Late…

200 papers

Latent-based image generative models, such as Latent Diffusion Models (LDMs) and Mask Image Models (MIMs), have achieved notable success in image generation tasks. These models typically leverage reconstructive autoencoders like VQGAN or…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Yongxin Zhu , Bocheng Li , Hang Zhang , Xin Li , Linli Xu , Lidong Bing

Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires expansive datasets, resulting…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Minhyun Lee , Song Park , Byeongho Heo , Dongyoon Han , Hyunjung Shim

Current approaches to pose generation rely heavily on intermediate representations, either through two-stage pipelines with quantization or autoregressive models that accumulate errors during inference. This fundamental limitation leads to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Yayuan Li , Filippos Bellos , Jason Corso

Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of…

Computer Vision and Pattern Recognition · Computer Science 2026-01-28 Feihong Yan , Peiru Wang , Yao Zhu , Kaiyu Pang , Qingyan Wei , Huiqi Li , Linfeng Zhang

Masked Image Modeling (MIM) with Vector Quantization (VQ) has achieved great success in both self-supervised pre-training and image generation. However, most existing methods struggle to address the trade-off in shared latent space for…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Siyuan Li , Luyuan Zhang , Zedong Wang , Juanxi Tian , Cheng Tan , Zicheng Liu , Chang Yu , Qingsong Xie , Haonan Lu , Haoqian Wang , Zhen Lei

Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive…

Machine Learning · Computer Science 2025-09-15 Omar Erak , Omar Alhussein , Hatem Abou-Zeid , Mehdi Bennis , Sami Muhaidat

Generative models serve as powerful tools for modeling the real world, with mainstream diffusion models, particularly those based on the latent diffusion model paradigm, achieving remarkable progress across various tasks, such as image and…

Machine Learning · Computer Science 2025-02-04 Wanghan Xu , Xiaoyu Yue , Zidong Wang , Yao Teng , Wenlong Zhang , Xihui Liu , Luping Zhou , Wanli Ouyang , Lei Bai

Tokenization and sub-tokenization based models like word2vec, BERT and the GPTs are the state-of-the-art in natural language processing. Typically, these approaches have limitations with respect to their input representation. They fail to…

Computation and Language · Computer Science 2026-02-26 Felix Schneider , Maria Gogolev , Sven Sickert , Joachim Denzler

Self-supervised learning (SSL) techniques have achieved remarkable results in various speech processing tasks. Nonetheless, a significant challenge remains in reducing the reliance on vast amounts of speech data for pre-training. This paper…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-05 Po-chun Hsu , Ali Elkahky , Wei-Ning Hsu , Yossi Adi , Tu Anh Nguyen , Jade Copet , Emmanuel Dupoux , Hung-yi Lee , Abdelrahman Mohamed

Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Despite their low inference cost, these approaches often suffer from training instability…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Tung Do , Thuan Hoang Nguyen , Hao Li

Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Hao Chen , Ze Wang , Xiang Li , Ximeng Sun , Fangyi Chen , Jiang Liu , Jindong Wang , Bhiksha Raj , Zicheng Liu , Emad Barsoum

We propose V2Flow, a novel tokenizer that produces discrete visual tokens capable of high-fidelity reconstruction, while ensuring structural and latent distribution alignment with the vocabulary space of large language models (LLMs).…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Guiwei Zhang , Tianyu Zhang , Mohan Zhou , Yalong Bai , Biye Li

Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation process is fragile; early token errors can cascade, which creates a clear need for…

Computation and Language · Computer Science 2025-10-06 Jian Mu , Qixin Zhang , Zhiyong Wang , Menglin Yang , Shuang Qiu , Chengwei Qin , Zhongxiang Dai , Yao Shu

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Maitreya Patel , Jingtao Li , Weiming Zhuang , Yezhou Yang , Lingjuan Lv

Token representations in high-dimensional latent spaces often exhibit redundancy, limiting computational efficiency and reducing structural coherence across model layers. Hierarchical latent space folding introduces a structured…

Computation and Language · Computer Science 2025-08-11 Fenella Harcourt , Naderdel Piero , Gilbert Sutherland , Daphne Holloway , Harriet Bracknell , Julian Ormsby

In this paper, we propose a simple yet effective transformer framework for self-supervised learning called DenseDINO to learn dense visual representations. To exploit the spatial information that the dense prediction tasks require but…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Yike Yuan , Xinghe Fu , Yunlong Yu , Xi Li

Modern large language models use a fixed tokenizer to effectively compress text drawn from a source domain. However, applying the same tokenizer to a new target domain often leads to inferior compression, more costly inference, and reduced…

Computation and Language · Computer Science 2024-11-07 Zhili Feng , Tanya Marwah , Nicolo Fusi , David Alvarez-Melis , Lester Mackey

The fundamental goal of self-supervised learning (SSL) is to produce useful representations of data without access to any labels for classifying the data. Modern methods in SSL, which form representations based on known or constructed…

Machine Learning · Computer Science 2022-09-30 Bobak T. Kiani , Randall Balestriero , Yubei Chen , Seth Lloyd , Yann LeCun

Semantic image synthesis, i.e., generating images from user-provided semantic label maps, is an important conditional image generation task as it allows to control both the content as well as the spatial layout of generated images. Although…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Tariq Berrada , Jakob Verbeek , Camille Couprie , Karteek Alahari

In this paper, we contend that the objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a mixture of low-dimensional Gaussian distributions supported on incoherent…

Machine Learning · Computer Science 2023-06-05 Yaodong Yu , Sam Buchanan , Druv Pai , Tianzhe Chu , Ziyang Wu , Shengbang Tong , Benjamin D. Haeffele , Yi Ma