{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:39:42Z","timestamp":1782833982154,"version":"3.54.5"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726422","type":"print"},{"value":"9783031726439","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72643-9_4","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T20:47:11Z","timestamp":1732222031000},"page":"54-69","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Efficient Inference of\u00a0Vision Instruction-Following Models with\u00a0Elastic Cache"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6943-3085","authenticated-orcid":false,"given":"Zuyan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benlin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-5378","authenticated-orcid":false,"given":"Guangyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3952-8753","authenticated-orcid":false,"given":"Yongming","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranjay","family":"Krishna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Aminabadi, R.Y., et\u00a0al.: Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale. In: SC22: International Conference for High Performance Computing, Networking, Storage and Analysis (2022)","DOI":"10.1109\/SC41404.2022.00051"},{"key":"4_CR2","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv:abs\/2308.12966 (2023)"},{"key":"4_CR3","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"4_CR4","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatGPT quality (2023). https:\/\/vicuna.lmsys.org. Accessed 14 Apr 2023"},{"key":"4_CR5","unstructured":"Dai, W., et al.: InstructBlip: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"4_CR6","unstructured":"Ge, S., Zhang, Y., Liu, L., Zhang, M., Han, J., Gao, J.: Model tells you what to discard: adaptive KV cache compression for LLMs. arXiv preprint arXiv:2310.01801 (2023)"},{"key":"4_CR7","unstructured":"Gong, T., et al.: Multimodal-GPT: a vision and language model for dialogue with humans. arXiv preprint arXiv:2305.04790 (2023)"},{"key":"4_CR8","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015)"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Hsieh, C.Y., et al.: Distilling step-by-step! Outperforming larger language models with less training data and smaller model sizes. arXiv preprint arXiv:2305.02301 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"4_CR10","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: International Conference on Machine Learning, pp. 4651\u20134664. PMLR (2021)"},{"key":"4_CR11","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"4_CR12","unstructured":"Lin, J., Tang, J., Tang, H., Yang, S., Dang, X., Han, S.: AWQ: activation-aware weight quantization for llm compression and acceleration. arXiv preprint arXiv:2306.00978 (2023)"},{"key":"4_CR13","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv:abs\/2310.03744 (2023)"},{"key":"4_CR14","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"4_CR15","unstructured":"Liu, Z., et al.: Scissorhands: exploiting the persistence of importance hypothesis for LLM KV cache compression at test time. arXiv preprint arXiv:2305.17118 (2023)"},{"key":"4_CR16","unstructured":"Liu, Z., Dong, Y., Rao, Y., Zhou, J., Lu, J.: Chain-of-spot: interactive reasoning improves large vision-language models. arXiv preprint arXiv:2403.12966 (2024)"},{"key":"4_CR17","unstructured":"Ma, X., Fang, G., Wang, X.: LLM-pruner: on the structural pruning of large language models. arXiv preprint arXiv:2305.11627 (2023)"},{"key":"4_CR18","unstructured":"Mu, J., Li, X.L., Goodman, N.: Learning to compress prompts with gist tokens. arXiv preprint arXiv:2304.08467 (2023)"},{"key":"4_CR19","unstructured":"OpenAI: GPT-4 technical report. arXiv:abs\/2303.08774 (2023). https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"4_CR20","unstructured":"OpenAI: GPT-4v(ision) system card. OpenAI Blog (2023). https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf"},{"key":"4_CR21","unstructured":"Ouyang, L., et\u00a0al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27730\u201327744 (2022)"},{"key":"4_CR22","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: HuggingGPT: solving AI tasks with chatGPT and its friends in huggingface. arXiv preprint arXiv:2303.17580 (2023)"},{"key":"4_CR23","unstructured":"Sheng, Y., et\u00a0al.: High-throughput generative inference of large language models with a single GPU. arXiv preprint arXiv:2303.06865 (2023)"},{"key":"4_CR24","unstructured":"Sun, M., Liu, Z., Bair, A., Kolter, J.Z.: A simple and effective pruning approach for large language models. arXiv preprint arXiv:2306.11695 (2023)"},{"key":"4_CR25","unstructured":"Taori, R., et al.: Stanford alpaca: an instruction-following llama model (2023). https:\/\/github.com\/tatsu-lab\/stanford_alpaca"},{"key":"4_CR26","unstructured":"Team, X.L.: Xwin-lm (2023). https:\/\/github.com\/Xwin-LM\/Xwin-LM"},{"key":"4_CR27","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"4_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"4_CR29","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)"},{"key":"4_CR30","unstructured":"Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., Han, S.: Smoothquant: accurate and efficient post-training quantization for large language models. In: International Conference on Machine Learning, pp. 38087\u201338099. PMLR (2023)"},{"key":"4_CR31","unstructured":"Xiao, G., Tian, Y., Chen, B., Han, S., Lewis, M.: Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453 (2023)"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Yang, J., et\u00a0al.: Octopus: embodied vision-language programmer from environmental feedback. arXiv preprint arXiv:2310.08588 (2023)","DOI":"10.1007\/978-3-031-73232-4_2"},{"key":"4_CR33","unstructured":"Yang, J., et al.: Learning embodied vision-language programming from instruction, exploration, and environmental feedback (2024). https:\/\/openreview.net\/forum?id=VUA9LSmC2r"},{"key":"4_CR34","unstructured":"Yang, Z., et al.: MM-react: prompting chatGPT for multimodal reasoning and action. arXiv preprint arXiv:2303.11381 (2023)"},{"key":"4_CR35","unstructured":"Yu, W., et al.: MM-vet: evaluating large multimodal models for integrated capabilities. arXiv:2308.02490 (2023)"},{"key":"4_CR36","unstructured":"Zhang, Z., et\u00a0al.: H $$ _2 $$ o: heavy-hitter oracle for efficient generative inference of large language models. arXiv preprint arXiv:2306.14048 (2023)"},{"key":"4_CR37","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72643-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T21:24:16Z","timestamp":1732224256000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72643-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726422","9783031726439"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72643-9_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}