{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T16:56:33Z","timestamp":1768409793065,"version":"3.49.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"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":[[2025,7,6]]},"DOI":"10.1109\/isvlsi65124.2025.11130305","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T18:20:15Z","timestamp":1756318815000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Efficient Deployment of Very Wide and Very Deep Hypersparse FFNs on FPGA"],"prefix":"10.1109","author":[{"given":"Paramdeep","family":"Singh","sequence":"first","affiliation":[{"name":"Santa Clara University,Computer Science and Engineering,Santa Clara,CA,USA"}]},{"given":"David C.","family":"Anastasiu","sequence":"additional","affiliation":[{"name":"Santa Clara University,Computer Science and Engineering,Santa Clara,CA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA51294.2020.00176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3508072.3508177"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/9781420010749"},{"key":"ref4","article-title":"Deep residual learning for image recognition","author":"He","year":"2015"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref6","article-title":"Text summarization using large language models: A comparative study of mpt-7b-instruct, falcon-7b-instruct, and openai chat-gpt models","author":"Basyal","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref8","article-title":"A survey of small language models","author":"Nguyen","year":"2024"},{"key":"ref9","article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","author":"Frantar","year":"2023"},{"key":"ref10","article-title":"Ultra-low precision 4-bit training of deep neural networks","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS \u201820","author":"Sun"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref12","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2016"},{"key":"ref13","article-title":"Slicegpt: Compress large language models by deleting rows and columns","author":"Ashkboos","year":"2024"},{"key":"ref14","article-title":"Llm-pruner: On the structural pruning of large language models","author":"Ma","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917312"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1145\/3020078.3021745","article-title":"Ese: Efficient speech recognition engine with sparse lstm on fpga","author":"Han","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392749"},{"key":"ref18","article-title":"A simple and effective pruning approach for large language models","author":"Sun","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916419"},{"key":"ref20","article-title":"Picking winning tickets before training by preserving gradient flow","author":"Wang","year":"2020"},{"key":"ref21","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","author":"Tanaka","year":"2020"},{"key":"ref22","article-title":"Snip: Single-shot network pruning based on connection sensitivity","author":"Lee","year":"2019"},{"key":"ref23","article-title":"A survey of lottery ticket hypothesis","author":"Liu","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ipdpsw.2019.00051"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1109\/URTC60662.2023.10534987","article-title":"Testing radix-nets: Advances in viable sparse topologies","author":"Kwak","year":"2023"}],"event":{"name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","location":"Kalamata, Greece","start":{"date-parts":[[2025,7,6]]},"end":{"date-parts":[[2025,7,9]]}},"container-title":["2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11129697\/11130193\/11130305.pdf?arnumber=11130305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:32:37Z","timestamp":1756355557000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130305\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/isvlsi65124.2025.11130305","relation":{},"subject":[],"published":{"date-parts":[[2025,7,6]]}}}