{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:48:01Z","timestamp":1772632081572,"version":"3.50.1"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T00:00:00Z","timestamp":1771113600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T00:00:00Z","timestamp":1771113600000},"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":[[2026,2,15]]},"DOI":"10.1109\/isscc49663.2026.11408987","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:50:24Z","timestamp":1772571024000},"page":"542-544","source":"Crossref","is-referenced-by-count":0,"title":["Tri-Oracle: A 17.78\u03bcJ\/Token Vision-Language Model Accelerator with Token-Attention-Weight Redundancy Prediction"],"prefix":"10.1109","author":[{"given":"Seungjae","family":"Yoo","sequence":"first","affiliation":[{"name":"KAIST,Daejeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hangyeol","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST,Daejeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muyoung","family":"Son","sequence":"additional","affiliation":[{"name":"KAIST,Daejeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Chen","sequence":"additional","affiliation":[{"name":"KAIST,Daejeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suheon","family":"Jeong","sequence":"additional","affiliation":[{"name":"KAIST,Daejeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joo-Young","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST,Daejeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"34892","article-title":"Visual Instruction Tuning","author":"Haotian","year":"2023","journal-title":"NeuIPS"},{"key":"ref2","article-title":"Tinyllava: A Framework of Small-Scale Large Multimodal Models","volume-title":"arXiv preprint arXiv","author":"Baichuan","year":"2024"},{"key":"ref3","article-title":"Improved Baselines with Visual Instruction Tuning","volume-title":"IEEE CVPR","author":"Haotian","year":"2024"},{"key":"ref4","article-title":"Llava-Next-Interleave: Tackling Multi-Image, Video, and 3D in Large Multimodal Models","volume-title":"arXiv preprint arXiv","author":"Feng","year":"2024"},{"key":"ref5","article-title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","volume-title":"arXiv preprint arXiv","author":"Guangxuan","year":"2024"},{"key":"ref6","first-page":"368","article-title":"C-Transformer: A 2.6-18.1 \u03bcJ\/ token Homogeneous DNN-Transformer\/Spiking-Transformer Processor with Big-Little Network and Implicit Weight Generation For Large Language Models","author":"Sangyeob","year":"2024","journal-title":"ISSCC"},{"key":"ref7","first-page":"406","article-title":"T-REX: A 68-to-567\u03bcs\/Token 0.41-to-3.95\u03bcJ\/Token Transformer Accelerator with Reduced External Memory Access and Enhanced Hardware Utilization in 16 nm FinFET","author":"Moon","year":"2025","journal-title":"ISSCC"},{"key":"ref8","article-title":"Token Merging: Your ViT but Faster","volume-title":"arXiv preprint arXiv","author":"Daniel","year":"2022"},{"key":"ref9","first-page":"64","article-title":"AdapTiV: Sign-Similarity Based Image-Adaptive Token Merging for Vision Transformer Acceleration","author":"Seungjae","year":"2024","journal-title":"ACM\/IEEE Micro"},{"key":"ref10","first-page":"248","article-title":"MuITCIM: A 28nm 2.24 \u03bcJ\/ Token Attention-Token-Bit Hybrid Sparse Digital CIM-Based Accelerator for Multimodal Transformers","author":"Fengbin","year":"2023","journal-title":"ISSCC"},{"key":"ref11","first-page":"250","article-title":"A 28nm 53.8 TOPS\/W 8b Sparse Transformer Accelerator with In-Memory Butterfly Zero Skipper for Unstructured-Pruned NN and CIM-Based Local-Attention-Reusable Engine","author":"Shiwei","year":"2023","journal-title":"ISSCC"},{"key":"ref12","first-page":"342","article-title":"A 12nm 18.1 TFLOPs\/W Sparse Transformer Processor with Entropy-Based Early Exit, Mixed-Precision Predication and Fine-Grained Power Management","author":"Thierry","year":"2023","journal-title":"ISSCC"},{"key":"ref13","article-title":"A 28nm 77.35 tops\/w Similar Vectors Traceable Transformer Processor with Principal-Component-Prior Speculating and Dynamic Bit-Wise Stationary Computing","volume-title":"IEEE Symp. VLSI Circuits","author":"Yang","year":"2023"}],"event":{"name":"2026 IEEE International Solid-State Circuits Conference (ISSCC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2026,2,15]]},"end":{"date-parts":[[2026,2,19]]}},"container-title":["2026 IEEE International Solid-State Circuits Conference (ISSCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408863\/11408946\/11408987.pdf?arnumber=11408987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T06:50:23Z","timestamp":1772607023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,15]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/isscc49663.2026.11408987","relation":{},"subject":[],"published":{"date-parts":[[2026,2,15]]}}}