English
Related papers

Related papers: REPA-E: Unlocking VAE for End-to-End Tuning with L…

200 papers

End-to-end learning of communication systems enables joint optimization of transmitter and receiver, implemented as deep neural network-based autoencoders, over any type of channel and for an arbitrary performance metric. Recently, an…

Information Theory · Computer Science 2019-06-25 Mathieu Goutay , Fayçal Ait Aoudia , Jakob Hoydis

While Reinforcement Learning (RL) agents can successfully learn to handle complex tasks, effectively generalizing acquired skills to unfamiliar settings remains a challenge. One of the reasons behind this is the visual encoders used are…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Yuhan Zhang , Guoqing Ma , Guangfu Hao , Liangxuan Guo , Yang Chen , Shan Yu

Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse, tending to generate conservative and homogeneous behaviors. While DiffusionDrive employs predefined anchors representing different driving…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Jialv Zou , Shaoyu Chen , Bencheng Liao , Zhiyu Zheng , Yuehao Song , Lefei Zhang , Qian Zhang , Wenyu Liu , Xinggang Wang

The surrogate loss of variational autoencoders (VAEs) poses various challenges to their training, inducing the imbalance between task fitting and representation inference. To avert this, the existing strategies for VAEs focus on adjusting…

Neural and Evolutionary Computing · Computer Science 2024-04-02 Zhangkai Wu , Longbing Cao , Lei Qi

Discrete latent bottlenecks in variational autoencoders (VAEs) offer high bit efficiency and can be modeled with autoregressive discrete distributions, enabling parameter-efficient multimodal search with transformers. However, discrete…

Machine Learning · Computer Science 2026-02-12 Michael Drolet , Firas Al-Hafez , Aditya Bhatt , Jan Peters , Oleg Arenz

Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Yian Zhao , Feng Wang , Qiushan Guo , Chang Liu , Xiangyang Ji , Jian Zhang , Jie Chen

An on-device DNN-HMM speech recognition system efficiently works with a limited vocabulary in the presence of a variety of predictable noise. In such a case, vocabulary and environment adaptation is highly effective. In this paper, we…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-25 Emiru Tsunoo , Yosuke Kashiwagi , Satoshi Asakawa , Toshiyuki Kumakura

Resolution generalization in image generation tasks enables the production of higher-resolution images with lower training resolution overhead. However, a key obstacle for diffusion transformers in addressing this problem is the mismatch…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Liang Hou , Cong Liu , Mingwu Zheng , Xin Tao , Pengfei Wan , Di Zhang , Kun Gai

Variational autoencdoers (VAE) are a popular approach to generative modelling. However, exploiting the capabilities of VAEs in practice can be difficult. Recent work on regularised and entropic autoencoders have begun to explore the…

Machine Learning · Computer Science 2022-03-02 Gregory A. Daly , Jonathan E. Fieldsend , Gavin Tabor

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

$\beta$-VAE is a follow-up technique to variational autoencoders that proposes special weighting of the KL divergence term in the VAE loss to obtain disentangled representations. Unsupervised learning is known to be brittle even on toy…

Machine Learning · Computer Science 2022-01-03 Miroslav Fil , Munib Mesinovic , Matthew Morris , Jonas Wildberger

This paper presents variable bitrate lossy image compression using a VAE-based neural network. An adaptable image quality adjustment strategy is proposed. The key innovation involves adeptly adjusting the input scale exclusively during the…

Image and Video Processing · Electrical Eng. & Systems 2024-09-11 Bouzid Arezki , Fangchen Feng , Anissa Mokraoui

Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Felix Krause , Timy Phan , Ming Gui , Stefan Andreas Baumann , Vincent Tao Hu , Björn Ommer

Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Wenxuan Wang , Fan Zhang , Yufeng Cui , Haiwen Diao , Zhuoyan Luo , Huchuan Lu , Jing Liu , Xinlong Wang

The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling…

Computer Vision and Pattern Recognition · Computer Science 2019-11-05 Jun Han , Salvator Lombardo , Christopher Schroers , Stephan Mandt

Variational autoencoders (VAE) are directed generative models that learn factorial latent variables. As noted by Burda et al. (2015), these models exhibit the problem of factor over-pruning where a significant number of stochastic factors…

Machine Learning · Computer Science 2017-08-08 Serena Yeung , Anitha Kannan , Yann Dauphin , Li Fei-Fei

Recent 3D content generation pipelines commonly employ Variational Autoencoders (VAEs) to encode shapes into compact latent representations for diffusion-based generation. However, the widely adopted uniform point sampling strategy in Shape…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Rui Chen , Jianfeng Zhang , Yixun Liang , Guan Luo , Weiyu Li , Jiarui Liu , Xiu Li , Xiaoxiao Long , Jiashi Feng , Ping Tan

The variational autoencoder (VAE) typically employs a standard normal prior as a regularizer for the probabilistic latent encoder. However, the Gaussian tail often decays too quickly to effectively accommodate the encoded points, failing to…

Machine Learning · Statistics 2024-03-05 Juno Kim , Jaehyuk Kwon , Mincheol Cho , Hyunjong Lee , Joong-Ho Won

Transformers have shown great potential in various computer vision tasks owing to their strong capability in modeling long-range dependency using the self-attention mechanism. Nevertheless, vision transformers treat an image as 1D sequence…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Yufei Xu , Qiming Zhang , Jing Zhang , Dacheng Tao

Automatic speech recognition (ASR) systems typically rely on an external endpointer (EP) model to identify speech boundaries. In this work, we propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) multitask…

Sound · Computer Science 2023-02-16 Shaan Bijwadia , Shuo-yiin Chang , Bo Li , Tara Sainath , Chao Zhang , Yanzhang He
‹ Prev 1 8 9 10 Next ›