{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:35:32Z","timestamp":1781714132887,"version":"3.54.5"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276245"],"award-info":[{"award-number":["62276245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02132","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22968-22977","source":"Crossref","is-referenced-by-count":1,"title":["Addressing Representation Collapse in Vector Quantized Models with One Linear Layer"],"prefix":"10.1109","author":[{"given":"Yongxin","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bocheng","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Xin","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihua","family":"Xia","sequence":"additional","affiliation":[{"name":"Jinan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linli","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","author":"Baevski","year":"2020"},{"key":"ref3","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref5","first-page":"4603","article-title":"Genie: Generative interactive environments","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Bruce","year":"2024"},{"key":"ref6","article-title":"High fidelity neural audio compression","volume-title":"Transactions on Machine Learning Research","author":"D\u00e9fossez","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.31998"},{"key":"ref11","first-page":"14096","article-title":"Straightening out the straight-through estimator: Overcoming optimization challenges in vector quantized net-works","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Huh","year":"2023"},{"key":"ref12","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net","author":"Jang","year":"2017"},{"key":"ref13","article-title":"Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling","author":"Ji","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","article-title":"Auto-encoding variational bayes","volume":"abs\/1312.6114","author":"Kingma","year":"2013","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref16","article-title":"Finite scalar quantization: VQ-VAE made simple","volume-title":"The Twelfth International Conference on Learning Representations","author":"Mentzer","year":"2024"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref18","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref19","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume-title":"Advances in Neural Information Processing Systems","author":"Razavi","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref22","article-title":"Theory and experiments on vector quantized autoencoders","author":"Roy","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref24","article-title":"Vocos: Closing the gap between timedomain and fourier-based neural vocoders for high-quality audio synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Siuzdak","year":"2024"},{"key":"ref25","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","first-page":"20987","article-title":"SQ-VAE: Variational Bayes on discrete representation with self-annealed stochastic quantization","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Takida","year":"2022"},{"key":"ref27","article-title":"Scaling laws with vocabulary: Larger models deserve larger vocabularies","author":"Tao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","article-title":"Chameleon: Mixed-modal early-fusion foundation models","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Neural discrete representation learning","volume-title":"Advances in Neural Information Processing Systems","author":"van den Oord","year":"2017"},{"key":"ref30","article-title":"Vector quantized wasserstein auto-encoder","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Vuong","year":"2023"},{"key":"ref31","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Scvae: Sparse coding-based variational autoencoder","volume":"abs\/2303.16666","author":"Xiao","year":"2023","journal-title":"ArXiv"},{"key":"ref33","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"International Conference on Learning Representations","author":"Yu","year":"2022"},{"key":"ref34","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref35","article-title":"Language model beats diffusion - tokenizer is key to visual generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01771"},{"key":"ref39","article-title":"Speechtokenizer: Unified speech tokenizer for speech language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"},{"key":"ref41","article-title":"High-quality pluralistic image completion via code shared vqgan","volume":"abs\/2204.01931","author":"Zheng","year":"2022","journal-title":"ArXiv"},{"key":"ref42","article-title":"Scaling the codebook size of vqgan to 100,000 with a utilization rate of 99%","volume":"abs\/2406.11837","author":"Zhu","year":"2024","journal-title":"ArXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0899"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.97"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446138.pdf?arnumber=11446138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:56Z","timestamp":1777530116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446138\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02132","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}