Vector-Quantized Variational Autoencoder

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 27

All topics

ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting
Oct 1, 2026Shibo Feng, Wanjin Feng, Yang Qiu +3Multivariate Time Series Forecasting Vector-Quantized Variational Autoencoder
Nanyang Technological University · Tsinghua University · Shanghai Jiao Tong University
Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacy
Sep 14, 2026Joseph Rowan, Buu Phan, Ashish J. KhistiChannel Vector-Quantized Variational Autoencoder
Department of Electrical and Computer Engineering, University of Toronto
Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving
Sep 3, 2026Ruoyu Yao, Yusen Xie, Qingzhao Liu +5Autonomous Driving Low-Latency Latent Planning
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China · Central Media Technology Institute, Huawei
Pitch Contour Tokenization using VQ-VAE and Its Application on Korean Traditional Music Analysis
Aug 11, 2026Seonguk Ju, Seola Cho, Sooin Chung +2Audio Tokenizers Vector-Quantized Variational Autoencoder
Music & Arts Learning (MALer) Lab, Sogang University, South Korea · Graduate School of Culture Technology, KAIST, South Korea
UniGen-AR: Unifying Visual Generation with Auto-Regressive Modeling
Jul 27, 2026Zhipeng Bao, Zhen Zhu, Nupur Kumari +4Autoregressive Image Generation Visual Generation
1Carnegie Mellon University · University of Illinois Urbana-Champaign · 3Toyota Research Institute
VQ-Touch: A Data-Efficient Tactile Generation Framework Across Sensors and Scenarios
Jul 16, 2026Kailin Lyu, Long Xiao, Jianing Zeng +3Tactile Contact-Rich Dexterous Manipulation
Institute of Automation, Chinese Academy of Sciences
Differentiable Clone-Structured Causal Graphs for End-to-End Cognitive Map Learning from Image Sequences
Jul 14, 2026Arash Nikzad, Sasan Sarbishegi, Ali Dasmeh +8Fuzzy Cognitive Map Class Activation Mapping
Goethe University Frankfurt, Frankfurt, Germany · Independent Researcher, Teheran, Iran · Max Planck Institute for Human Development, Berlin, Germany +8
Low-Latency Task-Oriented Image Transmission with Opportunistic Spectrum Access
Jul 2, 2026João Henrique Inacio de Souza, Mattia Merluzzi, Mateus P. Mota +2Source-Channel Coding Vector-Quantized Variational Autoencoder
Department of Electronic Systems, Aalborg University, Aalborg, Denmark. · CEA-Leti, Université Grenoble Alpes, F-38000 Grenoble, France. · Telecommunications Research Institute, Universidad de Málaga, Málaga, Spain.
Integrating Facial Generation into Full-Duplex Spoken Dialogue Systems
Jun 20, 2026Jingjing Jiang, Atsumoto Ohashi, Ryuichiro HigashinakaFull-Duplex Speech Models Audio-Video Generation
Graduate School of Informatics, Nagoya University, Japan
Sustainable Face Recognition on Low-Power Devices with VQ-VAE Embeddings
Jun 13, 2026Christos Chronis, Georgios Th. Papadopoulos, Iraklis VarlamisEdge Devices Face Recognition Model
Dep. of Informatics and Telematics Harokopio University of Athens Athens, Greece
Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
Jun 11, 2026Xiang Li, Yixuan Zhou, Jingran Xie +2Neural Speech Codecs Neural Codecs
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China
EEGDancer: Dynamic Emotion Latent Space Masked Modeling with Reinforcement Learning for EEG Continuous Emotion Prediction
Jun 4, 2026Zhihao Zhou, Weishan Ye, Li Zhang +2Vector-Quantized Variational Autoencoder Latent Space
The School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, China · The Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound2026 Imaging, Shenzhen, China
C2GA: A Class-Controllable Generative Augmentation Framework for Respiratory Sound Classification
Jun 1, 2026Ziqi Ma, Mengyu Han, Anteng Cai +4Respiratory Sound Classification Conditional Variational Autoencoder
aSchool of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China · bSchool of AI and Advanced Computing (AIAC), XJTLU Entrepreneur College (Taicang), Xi’an Jiaotong-Liverpool University, Taicang, Suzhou, 215400, China · cISIR, Osaka University, Suita, 567-0047, Osaka, Japan
Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models
May 31, 2026Yunhao Zhang, Ruiying Qi, Jiale Zheng +3Time Series Foundation Models Time Series
Shanghai Jiao Tong University · Huawei Noah’s Ark Lab
Channel-wise Vector Quantization
May 25, 2026Wei Song, Tianhang Wang, Yitong Chen +5Autoregressive Image Generation Visual Tokenizers
Shanghai Innovation Institute · Westlake University · Zhejiang University +2
BandVQ: Band-Wise Vector-Quantized EEG Foundation Model
May 24, 2026Jamiyan Sukhbaatar, Satoshi Imamura, Toshihisa TanakaElectroencephalography Foundation Models Electroencephalography
National University of Mongolia, Ulaanbaatar, Mongolia · Tokyo University of Agriculture and Technology, Tokyo, Japan
MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots
May 23, 2026Yusen Feng, Xiang Wang, Heyuan Yao +7Full-Body Humanoid Control Agile Locomotion
Peking University
Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates
May 21, 2026Guojun Xu, Mingyang Zhang, Jianwen Xiang +3Learned Image Compression Ultra-Low Bitrates
School of Computer Science and Artificial Intelligence, Wuhan University of Technology
Composable Crystals: Controllable Materials Discovery via Concept Learning
May 14, 2026Nian Liu, Yuwei Zeng, Ryoji Kubo +7Crystal Data-Driven Materials Discovery
National University of Singapore · Loyola Marymount University
SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-Commerce Agents
May 14, 2026Zahra Zanjani Foumani, Alberto Castelo, Shuang Xie +3Agentic Commerce User Simulation
Shopify · Bellevue, Washington, USA
ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
May 13, 2026Jaeyung Kim, YoungJoon YooVector-Quantized Variational Autoencoder Residual Vector Quantization
Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea · SNUAILAB, Seoul, Republic of Korea
Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse
May 7, 2026Xinyu Zhao, Nikita Karagodin, Hamed Hassani +3Vector-Quantized Variational Autoencoder Codebooks
MIT
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
May 2, 2026Guotao Liang, Zhangcheng Wang, Chuang Wang +6Vector-Quantized Variational Autoencoder Sketches
School of Software, Beihang University, Beijing, China · College of Computer Science and Technology, Zhejiang University, Hangzhou, China · Paradigm 3 +1
VQ-SAD: Vector Quantized Structure Aware Diffusion For Molecule Generation
May 1, 2026Farshad Noravesh, Reza Haffari, Layki Soon +1Molecular Generation Vector-Quantized Variational Autoencoder
Cross-Layer Discrete Concept Discovery for Interpreting Language Models
Jun 24, 2025Ankur Garg, Xuemin Yu, Hassan Sajjad +1Vector-Quantized Variational Autoencoder Cross-Encoder
REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering
Jun 10, 2025Li-Ming Zhan, Bo Liu, Chengqiang Xie +2Linear Activation Steering Truth
Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong S.A.R.
Using Seismic Statistical Features and VQ-VAE to Improve Spatiotemporal Seismicity Predictability
Date pendingWei Quan, Denise GorseFull Waveform Inversion Vector-Quantized Variational Autoencoder
Department of Computer Science University College London

Oct 1, 2026, cs.AIJ/K move · Enter open · S save

ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting

Shibo Feng, Wanjin Feng, Yang Qiu, Deheng Ye+2

Nanyang Technological University · Tsinghua University · Shanghai Jiao Tong University

Multivariate Time Series Forecasting Vector-Quantized Variational Autoencoder Multivariate Time-Series Autoregressive Model Time Series

Open paper AskPDF arXiv

Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-based methods achieve competitive performance but typically require many sampling steps at inference. VAE-based non-iterative forecasting frameworks have therefore emerged as an efficient alternative. Within this line of work, vector quantization (VQ) enables controllable latent space modeling by mapping multivariate series into compact discrete representations. Existing VQ-based forecasting methods, however, typically rely on autoregressive (AR) token generation, which suffers from exposure bias and training-inference mismatch. Flow matching provides an efficient non-autoregressive alternative for latent forecasting, but existing formulations usually initialize transport from a generic Gaussian prior. We instead observe that the trained VQ codebook already captures representative latent prototypes and can thus serve as a more informative prior for flow matching. Based on this insight, we propose ProtoFlow, a forecasting framework that combines vector-quantized autoencoding with Prototype-prior Flow matching. Our method first maps multivariate sequences into a discrete latent space, then constructs a structured prior from the learned codebook, and finally learns a DiT-based rectified flow to transport samples from this prior to future latent representations conditioned on historical observations. By replacing generic noise initialization with a learned prototype prior, ProtoFlow avoids the rollout mismatch of AR token prediction and promotes faster training convergence. Extensive experiments on benchmark datasets show that it consistently achieves superior forecasting performance with efficient inference.

Momentum

Related topics

Latest papers 27