{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:20:52Z","timestamp":1778048452720,"version":"3.51.4"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00081","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"762-772","source":"Crossref","is-referenced-by-count":0,"title":["DICE: Discrete Inversion Enabling Controllable Editing for Masked Generative Models"],"prefix":"10.1109","author":[{"given":"Xiaoxiao","family":"He","sequence":"first","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Dao","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ligong","family":"Han","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Wen","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minhao","family":"Bai","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Liu","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Juefei-Xu","sequence":"additional","affiliation":[{"name":"NYU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaowei","family":"Tan","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin Renqiang","family":"Min","sequence":"additional","affiliation":[{"name":"NEC Labs America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang","family":"Li","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faez","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akash","family":"Srivastava","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongdong","family":"Li","sequence":"additional","affiliation":[{"name":"ANU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junzhou","family":"Huang","sequence":"additional","affiliation":[{"name":"UT Arlington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitris N.","family":"Metaxas","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Block diffusion: Interpolating between autoregressive and diffusion language models","author":"Arriola","year":"2025"},{"key":"ref3","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume":"34","author":"Austin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_11"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1102"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref8","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref10","first-page":"31","article-title":"Neural ordinary differential equations","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Diffusion posterior sampling for general noisy inverse problems","author":"Chung","year":"2022"},{"key":"ref12","article-title":"Flow matching in latent space","author":"Dao","year":"2023"},{"key":"ref13","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref14","first-page":"3518","article-title":"Imagebart: Bidirectional context with multinomial diffusion for autoregressive image synthesis","volume":"34","author":"Esser","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_23"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4239"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00360"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00424"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43990-2_13"},{"key":"ref23","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref25","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume":"34","author":"Hoogeboom","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref27","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016"},{"key":"ref28","article-title":"Direct inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2023"},{"key":"ref29","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022"},{"key":"ref30","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022"},{"key":"ref31","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref32","article-title":"Discrete diffusion language modeling by estimating the ratios of the data distribution","author":"Lou","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref34","first-page":"27","article-title":"A* sampling","author":"Maddison","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2502"},{"key":"ref36","article-title":"Sdedit: Image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00207"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00585"},{"key":"ref39","article-title":"Large language diffusion models","author":"Nie","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01458"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref43","article-title":"A novel sampling scheme for text-and image-conditional image synthesis in quantized latent spaces","author":"Rampas","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4135"},{"key":"ref46","article-title":"Lightning-fast image inversion and editing for text-to-image diffusion models","author":"Samuel","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3277"},{"key":"ref48","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International Conference on Machine Learning","author":"Sohl-Dickstein"},{"key":"ref49","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref50","first-page":"32","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00092"},{"key":"ref53","article-title":"Ledits: Real image editing with ddpm inversion and semantic guidance","author":"Tsaban","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref55","article-title":"Bert has a mouth, and it must speak: Bert as a markov random field language model","author":"Wang","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref57","volume-title":"Gumbel distribution \u2014 Wikipedia, The Free Encyclopedia","year":"2024"},{"key":"ref58","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref59","article-title":"Unifying diffusion models\u2019 latent space, with applications to cyclediffusion and guidance","author":"Wu","year":"2022"},{"key":"ref60","author":"Ye","year":"2025","journal-title":"Dream 7b"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"ref64","article-title":"A reparameterized discrete diffusion model for text generation","author":"Zheng","year":"2023"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492502.pdf?arnumber=11492502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:04:17Z","timestamp":1778047457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492502\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00081","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}