method · first seen 13 Oct 2026
residual quantized variational autoencoder
Also: RQ-VAE, VQ-VAE, vector-quantized autoencoder, vector-quantized variational autoencoder, residual quantization variational autoencoder
A VAE that encodes inputs into discrete codes via stacked residual quantization, yielding hierarchical coarse-to-fine tokens.
Mentions per week
PapersCodeDiscussion
Rank 149 on 1 Nov 2026 · 6 mentions in 28 days · 6 independent groups · papers · first seen 3 weeks ago · acceleration -0.59
Earliest sources
- FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion RetrievalPapers · 13 Oct 2026 · Tripti Shukla, Shwetha Somasundaram, Akshat Gupta, Rohit Garg, Paul Duff, Ian An…
- ViMoLa: Discrete Motion Tokens for Language-Guided Video GenerationPapers · 18 Oct 2026 · Bishoy Galoaa, Sarah Ostadabbas
- ORBIT: Autoregressive Time Series Generation via Next Frequency-Band PredictionPapers · 19 Oct 2026 · Chunyi Hou, Xiangfei Qiu, Hanyin Cheng, Chenchen Sun, Yisheng An, Yang Shu, Jili…
- QECGBERT: A Scalable ECG Foundation Model Based on Self-Supervised Language Learning via VQ-VAE Waveform TokenizationPapers · 25 Oct 2026 · Aruna Mohan, Burcu Ozek, Or Zilbershot, Fatemeh Afghah
- Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook CollapsePapers · 26 Oct 2026 · Yuwei Zeng, Zekun Shi
- CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained OptimizationPapers · 28 Oct 2026 · Zhiyuan Xiang, Xiang Deng, Wanjie Tao, Xu Chen, Zhao Jielun, Weili Guan
Latest sources
- ScrewSense: Mapping the Invisible - Anomaly Detection and Error Classification in Screwdriving ProcessesPapers · 12 Nov 2026 · Tobias Lettner, Tatyana Ivanovska, Anwar Al Assadi, Christian Bergler
- MV-Sign: Multi-View 3D Motion Integration and Enhanced Text-to-Motion Conditioning for Sign Language ProductionPapers · 5 Nov 2026 · Singyu Muk, Kaustubh Kundu, Kunyuan Xie, Weijie Wang, Kalin Stefanov
- BRIDGE: Bridging the Semantic Quantization Gap for Generative RecommendationPapers · 5 Nov 2026 · Yatong Xiao, Mingjie Sun, Peng Wang, Wenjin Wu, Peng Jiang
- CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained OptimizationPapers · 28 Oct 2026 · Zhiyuan Xiang, Xiang Deng, Wanjie Tao, Xu Chen, Zhao Jielun, Weili Guan
- Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook CollapsePapers · 26 Oct 2026 · Yuwei Zeng, Zekun Shi
- QECGBERT: A Scalable ECG Foundation Model Based on Self-Supervised Language Learning via VQ-VAE Waveform TokenizationPapers · 25 Oct 2026 · Aruna Mohan, Burcu Ozek, Or Zilbershot, Fatemeh Afghah
- ORBIT: Autoregressive Time Series Generation via Next Frequency-Band PredictionPapers · 19 Oct 2026 · Chunyi Hou, Xiangfei Qiu, Hanyin Cheng, Chenchen Sun, Yisheng An, Yang Shu, Jili…
- ViMoLa: Discrete Motion Tokens for Language-Guided Video GenerationPapers · 18 Oct 2026 · Bishoy Galoaa, Sarah Ostadabbas
- FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion RetrievalPapers · 13 Oct 2026 · Tripti Shukla, Shwetha Somasundaram, Akshat Gupta, Rohit Garg, Paul Duff, Ian An…