{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:01:27Z","timestamp":1780639287800,"version":"3.54.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"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":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539302","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["FLARE: Finetuning ReLU With FIRE for Efficient Long-Context Inference"],"prefix":"10.23919","author":[{"given":"Michael","family":"Moffatt","sequence":"first","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyi","family":"Luo","sequence":"additional","affiliation":[{"name":"Brown University,Providence,RI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qilong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinting","family":"Jiang","sequence":"additional","affiliation":[{"name":"Brown University,Providence,RI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanchen","family":"Tao","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiwei","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kauna","family":"Lei","sequence":"additional","affiliation":[{"name":"Brown University,Providence,RI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory","family":"Kielian","sequence":"additional","affiliation":[{"name":"Google Research,Mountain View,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehdi","family":"Saligane","sequence":"additional","affiliation":[{"name":"Brown University,Providence,RI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref3","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dao"},{"key":"ref4","article-title":"Replacing softmax with relu in vision transformers","author":"Wortsman","year":"2023"},{"key":"ref5","article-title":"A study on relu and softmax in transformer","author":"Shen","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.523"},{"key":"ref7","article-title":"Roformer: Enhanced transformer with rotary position embedding","author":"Su","year":"2023"},{"key":"ref8","article-title":"Extending context window of large language models via positional interpolation","author":"Chen","year":"2023"},{"key":"ref9","article-title":"Functional interpolation for relative positions improves long context transformers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li"},{"key":"ref10","article-title":"You can remove gpt2\u2019s layernorm by fine-tuning","author":"Heimersheim","year":"2024"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52734.2025.01388","article-title":"Transformers without normalization","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhu"},{"key":"ref12","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","author":"Martins","year":"2016"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1146","article-title":"Sparse sequence-to-sequence models","author":"Peters","year":"2019"},{"key":"ref14","article-title":"Rethinking softmax: Self-attention with polynomial activations","author":"Hemanth","year":"2024"},{"key":"ref15","article-title":"Attention with linear biases (alibi)","author":"Press","year":"2022"},{"key":"ref16","article-title":"A length-extrapolatable transformer","author":"Sun","year":"2022"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.52202\/068431-0610","article-title":"Kerple: Kernelized relative positional embedding for length extrapolation","author":"Chi","year":"2022"},{"key":"ref18","article-title":"Transformers can do arithmetic with the right embeddings","author":"McLeish","year":"2024"},{"key":"ref19","article-title":"Openwebtext corpus","author":"Gokaslan","year":"2019"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref21","article-title":"Online normalizer calculation for softmax","author":"Milakov","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED58423.2023.10244348"}],"event":{"name":"2026 Design, Automation & Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539302.pdf?arnumber=11539302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:12:06Z","timestamp":1780636326000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":23,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539302","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}