{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T05:58:21Z","timestamp":1785563901766,"version":"3.56.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation","award":["OAC-2311875,OAC-2514036,OAC-2513768"],"award-info":[{"award-number":["OAC-2311875,OAC-2514036,OAC-2513768"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/ccgrid68966.2026.00022","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T18:07:54Z","timestamp":1785521274000},"page":"126-135","source":"Crossref","is-referenced-by-count":0,"title":["EmbdC: Error-Bounded Lossy Video Embedding Compression for On-Device LLM Inference"],"prefix":"10.1109","author":[{"given":"Bo","family":"Jiang","sequence":"first","affiliation":[{"name":"Temple University","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taolue","family":"Yang","sequence":"additional","affiliation":[{"name":"Temple University","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Temple University","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xubin","family":"He","sequence":"additional","affiliation":[{"name":"Temple University","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Di","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory","place":["Lemont, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sian","family":"Jin","sequence":"additional","affiliation":[{"name":"Temple University","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3566695"},{"key":"ref3","article-title":"Qwen2. 5-vl technical report","volume-title":"arXiv preprint","author":"Bai","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"ref5","article-title":"Splitllm: Collaborative inference of 1lms for model placement and throughput optimization","author":"Mudvari","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Merge, ensemble, and cooperate! a survey on collaborative strategies in the era of large language models","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref8","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref11","article-title":"Internv13: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3201176"},{"key":"ref13","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"19","article-title":"An image is worth 1\/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models","volume-title":"European Conference on Computer Vision","author":"Chen","year":"2024"},{"key":"ref15","article-title":"Exploring and evaluating hallucinations in llm-powered code generation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.30935\/cedtech\/13605"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.09.178"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref19","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.05.022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00021"},{"key":"ref22","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3307681.3326608"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710852"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.14778\/3503585.3503597"},{"key":"ref26","article-title":"Kvcomp: A high-performance, llm-aware, lossy compression framework for kv cache","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Packkv: Reducing kv cache memory footprint through 1lm-aware lossy compression","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3201176"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414624"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref32","article-title":"Vinoground: Scrutinizing lmms over dense temporal reasoning with short videos","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755203"}],"event":{"name":"2026 IEEE 26th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","location":"Sydney, Australia","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["2026 IEEE 26th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11618979\/11618983\/11619056.pdf?arnumber=11619056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T05:10:50Z","timestamp":1785561050000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11619056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ccgrid68966.2026.00022","relation":{},"subject":[],"published":{"date-parts":[[2026,5]]}}}