{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:22:01Z","timestamp":1774419721619,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889322","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Large Language Models via Attention Shortcuts"],"prefix":"10.1109","author":[{"given":"Prateek","family":"Verma","sequence":"first","affiliation":[{"name":"Stanford University,Department of Electrical Engineering,Stanford,CA,94305"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mert","family":"Pilanci","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Electrical Engineering,Stanford,CA,94305"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768298"},{"key":"ref4","article-title":"Music transformer: Generating music with long-term structure","volume-title":"International Conference on Learning Representations (ICLR)","author":"Huang"},{"key":"ref5","article-title":"A framework for contrastive and generative learning of audio representations","author":"Verma","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref7","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021"},{"key":"ref8","article-title":"Gemini: a family of highly capable multimodal models","year":"2023"},{"key":"ref9","article-title":"Chameleon: Mixed-modal earlyfusion foundation models","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1419"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref12","article-title":"Utilizing bert intermediate layers for aspect based sentiment analysis and natural language inference","author":"Song","year":"2020"},{"key":"ref13","article-title":"Don\u2019t judge a language model by its last layer: Contrastive learning with layer-wise attention pooling","author":"Oh","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2193"},{"key":"ref16","article-title":"Linearity of relation decoding in transformer language models","author":"Hernandez","year":"2024","journal-title":"ICLR"},{"issue":"240","key":"ref17","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","article-title":"High fidelity neural audio compression","author":"Defossez","year":"2022"},{"key":"ref20","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref21","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hawthorne"},{"key":"ref22","first-page":"8535","article-title":"General-purpose, long-context autoregressive modeling with perceiver ar","volume-title":"International Conference on Machine Learning","author":"Hawthorne"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013159"},{"key":"ref24","article-title":"Megabyte: Predicting million-byte sequences with multiscale transformers","volume":"36","author":"Yu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889322.pdf?arnumber=10889322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:18Z","timestamp":1774416258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889322","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}