{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:47:31Z","timestamp":1792025251406,"version":"4.4.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370976","type":"print"},{"value":"9783032370983","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37098-3_12","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:09:35Z","timestamp":1788944975000},"page":"204-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FastSTAR: Spatiotemporal Token Pruning for\u00a0Efficient Autoregressive Video Synthesis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5440-9265","authenticated-orcid":false,"given":"Sungwoong","family":"Yune","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suheon","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joo-Young","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"12_CR1","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your vit but faster (2023). https:\/\/arxiv.org\/abs\/2210.09461"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 4599\u20134603 (2023)","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: Pixart-$$\\sigma $$: weak-to-strong training of diffusion transformer for 4k text-to-image generation (2024). https:\/\/arxiv.org\/abs\/2403.04692","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"12_CR4","unstructured":"Chen, J., et al.: Pixart-$$\\delta $$: fast and controllable image generation with latent consistency models (2024). https:\/\/arxiv.org\/abs\/2401.05252"},{"key":"12_CR5","unstructured":"Chen, J., et al.: Pixart-$$\\alpha $$: fast training of diffusion transformer for photorealistic text-to-image synthesis (2023). https:\/\/arxiv.org\/abs\/2310.00426"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Fan, J., Yu, Z., Zhuang, B., Tan, M.: Frequency-aware autoregressive modeling for efficient high-resolution image synthesis (2025). https:\/\/arxiv.org\/abs\/2507.20454","DOI":"10.1109\/ICCV51701.2025.01592"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Ma, X., Fang, G., Wang, X.: Collaborative decoding makes visual auto-regressive modeling efficient. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23334\u201323344 (2025)","DOI":"10.1109\/CVPR52734.2025.02173"},{"key":"12_CR8","unstructured":"Deng, H., et al.: Autoregressive video generation without vector quantization (2025). https:\/\/arxiv.org\/abs\/2412.14169"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Fang, H., Tang, S., Cao, J., Zhang, E., Tang, F., Lee, T.Y.: Attend to not attended: structure-then-detail token merging for post-training DIT acceleration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18083\u201318092 (2025)","DOI":"10.1109\/CVPR52734.2025.01685"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Guo, H., et al.: Fastvar: linear visual autoregressive modeling via cached token pruning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19011\u201319021 (2025)","DOI":"10.1109\/ICCV51701.2025.01767"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Han, J., et al.: Infinity: scaling bitwise autoregressive modeling for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15733\u201315744 (2025)","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"12_CR12","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020). https:\/\/arxiv.org\/abs\/2006.11239"},{"key":"12_CR13","unstructured":"Huang, Z., et al.: Vbench: comprehensive benchmark suite for video generative models (2023). https:\/\/arxiv.org\/abs\/2311.17982"},{"key":"12_CR14","unstructured":"Ji, L., et al.: Videoar: autoregressive video generation via next-frame & scale prediction (2026). https:\/\/arxiv.org\/abs\/2601.05966"},{"key":"12_CR15","unstructured":"Kong, W., et al.: Hunyuanvideo: a systematic framework for large video generative models (2025). https:\/\/arxiv.org\/abs\/2412.03603"},{"key":"12_CR16","unstructured":"Li, J., Ma, Y., Zhang, X., Wei, Q., Liu, S., Zhang, L.: Skipvar: accelerating visual autoregressive modeling via adaptive frequency-aware skipping (2025). https:\/\/arxiv.org\/abs\/2506.08908"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Li, K., Chen, Z., Yang, C.Y., Hwang, J.N.: Memory-efficient visual autoregressive modeling with scale-aware KV cache compression (2025). https:\/\/arxiv.org\/abs\/2505.19602","DOI":"10.52202\/085713-0462"},{"key":"12_CR18","unstructured":"Li, K., Shah, M., Shang, Y.: Packcache: a training-free acceleration method for unified autoregressive video generation via compact KV-cache (2026). https:\/\/arxiv.org\/abs\/2601.04359"},{"key":"12_CR19","unstructured":"Li, S., Wang, K., Khan, S., Khan, F.S., Yang, J., Wang, Y.: Stagevar: stage-aware acceleration for visual autoregressive models (2025). https:\/\/arxiv.org\/abs\/2512.16483"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., Ma, C., Yang, X., Yang, M.H.: Vidtome: video token merging for zero-shot video editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7486\u20137495 (2024)","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"12_CR21","unstructured":"Lin, S., Yang, X.: Animatediff-lightning: cross-model diffusion distillation (2024). https:\/\/arxiv.org\/abs\/2403.12706"},{"key":"12_CR22","unstructured":"Liu, J., et al.: Infinitystar: unified spacetime autoregressive modeling for visual generation (2025). https:\/\/arxiv.org\/abs\/2511.04675"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., LI, C., Zhu, J.: DPM-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 5775\u20135787. Curran Associates, Inc. (2022). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/260a14acce2a89dad36adc8eefe7c59e-Paper-Conference.pdf","DOI":"10.52202\/068431-0418"},{"key":"12_CR24","unstructured":"Lu, W., Zheng, S., Xia, Y., Wang, S.: Toma: token merge with attention for diffusion models (2025). https:\/\/arxiv.org\/abs\/2509.10918"},{"key":"12_CR25","unstructured":"Lv, Z., et al.: Fastercache: training-free video diffusion model acceleration with high quality (2025). https:\/\/arxiv.org\/abs\/2410.19355"},{"key":"12_CR26","unstructured":"Ren, S., et al.: Autoregressive video generation beyond next frames prediction (2025). https:\/\/arxiv.org\/abs\/2509.24081"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022). https:\/\/arxiv.org\/abs\/2112.10752","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR28","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2022). https:\/\/arxiv.org\/abs\/2010.02502"},{"key":"12_CR29","doi-asserted-by":"publisher","unstructured":"Su, S., Liu, J., Gao, L., Song, J.: $$\\text{F}^{3}$$-pruning: a training-free and generalized pruning strategy towards faster and finer text-to-video synthesis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 5, pp. 4961\u20134969 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i5.28300. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/28300","DOI":"10.1609\/aaai.v38i5.28300"},{"key":"12_CR30","unstructured":"Sun, W., Tu, R.C., Liao, J., Jin, Z., Tao, D.: Asymrnr: video diffusion transformers acceleration with asymmetric reduction and restoration. In: International Conference on Machine Learning, pp. 57694\u201357711. PMLR (2025)"},{"key":"12_CR31","doi-asserted-by":"publisher","unstructured":"Tian, K., Jiang, Y., Yuan, Z., Peng, B., Wang, L.: Visual autoregressive modeling: scalable image generation via next-scale prediction. In: Globerson, A., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a037, pp. 84839\u201384865. Curran Associates, Inc. (2024). https:\/\/doi.org\/10.52202\/079017-2694. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/9a24e284b187f662681440ba15c416fb-Paper-Conference.pdf","DOI":"10.52202\/079017-2694"},{"key":"12_CR32","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models (2025). https:\/\/arxiv.org\/abs\/2503.20314"},{"key":"12_CR33","unstructured":"Wang, X., et al.: Videolcm: video latent consistency model (2023). https:\/\/arxiv.org\/abs\/2312.09109"},{"key":"12_CR34","unstructured":"Wang, X., et al.: Emu3: next-token prediction is all you need (2024). https:\/\/arxiv.org\/abs\/2409.18869"},{"key":"12_CR35","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: Videogpt: video generation using VQ-VAE and transformers (2021). https:\/\/arxiv.org\/abs\/2104.10157"},{"key":"12_CR36","unstructured":"Yang, Z., et al.: Cogvideox: text-to-video diffusion models with an expert transformer (2025). https:\/\/arxiv.org\/abs\/2408.06072"},{"key":"12_CR37","unstructured":"Ye, Y., et al.: Fast autoregressive video generation with diagonal decoding (2025). https:\/\/arxiv.org\/abs\/2503.14070"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: Magvit: masked generative video transformer. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10459\u201310469. IEEE Computer Society (2023)","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"12_CR39","unstructured":"Yu, L., et al.: Language model beats diffusion \u2013 tokenizer is key to visual generation (2024). https:\/\/arxiv.org\/abs\/2310.05737"},{"key":"12_CR40","unstructured":"Yuan, H., et al.: Lumos-1: on autoregressive video generation from a unified model perspective (2025). https:\/\/arxiv.org\/abs\/2507.08801"},{"key":"12_CR41","doi-asserted-by":"publisher","unstructured":"Zhai, Y., et al.: Motion consistency model: Accelerating video diffusion with disentangled motion-appearance distillation. In: Globerson, A., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a037, pp. 111000\u2013111021. Curran Associates, Inc. (2024). https:\/\/doi.org\/10.52202\/079017-3524. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/c859b99b5d717c9035e79d43dfd69435-Paper-Conference.pdf","DOI":"10.52202\/079017-3524"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, E., Tang, J., Ning, X., Zhang, L.: Training-free and hardware-friendly acceleration for diffusion models via similarity-based token pruning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 9878\u20139886 (2025)","DOI":"10.1609\/aaai.v39i9.33071"},{"key":"12_CR43","unstructured":"Zhang, E., et al.: Token pruning for caching better: 9 times acceleration on stable diffusion for free (2024). https:\/\/arxiv.org\/abs\/2501.00375"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric (2018). https:\/\/arxiv.org\/abs\/1801.03924","DOI":"10.1109\/CVPR.2018.00068"},{"key":"12_CR45","unstructured":"Zhao, Y., Xiong, Y., Kr\u00e4henb\u00fchl, P.: Image and video tokenization with binary spherical quantization (2024). https:\/\/arxiv.org\/abs\/2406.07548"},{"key":"12_CR46","unstructured":"Zhou, X., et al.: Less is enough: training-free video diffusion acceleration via runtime-adaptive caching (2025). https:\/\/arxiv.org\/abs\/2507.02860"},{"key":"12_CR47","unstructured":"Zou, C., Liu, X., Liu, T., Huang, S., Zhang, L.: Accelerating diffusion transformers with token-wise feature caching (2025). https:\/\/arxiv.org\/abs\/2410.05317"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37098-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:17:32Z","timestamp":1792023452000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37098-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370976","9783032370983"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37098-3_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}