Jekyll2025-01-27T08:06:06+00:00https://proceedings.mlr.press/v262/feed.xmlProceedings of Machine Learning ResearchProceedings of The 4th NeurIPS Efficient Natural Language and Speech Processing Workshop
Held in Vancouver, British Columbia, Canada on 14 December 2024
Published as Volume 262 by the Proceedings of Machine Learning Research on 10 December 2024.
Volume Edited by:
Mehdi Rezagholizadeh
Peyman Passban
Soheila Samiee
Vahid Partovi Nia
Yu Cheng
Yue Deng
Qun Liu
Boxing Chen
Series Editors:
Neil D. Lawrence
PMLRAdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/agrawal24a[{"given"=>"Sudhanshu", "family"=>"Agrawal"}, {"given"=>"Wonseok", "family"=>"Jeon"}, {"given"=>"Mingu", "family"=>"Lee"}]SuperPos-Prompt: Enhancing Soft Prompt Tuning of Language Models with Superposition of Multi Token Embeddings2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/ali-sadraei-javaheri24a[{"given"=>"Mohammad", "family"=>"Ali Sadraei Javaheri"}, {"given"=>"Ehsaneddin", "family"=>"Asgari"}, {"given"=>"Alice", "family"=>"C. McHardy"}, {"given"=>"Hamid", "family"=>"R. Rabiee"}]Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/alizadeh-vahid24a[{"given"=>"Keivan", "family"=>"Alizadeh-Vahid"}, {"given"=>"Seyed", "family"=>"Iman Mirzadeh"}, {"given"=>"Hooman", "family"=>"Shahrkokhi"}, {"given"=>"Dmitry", "family"=>"Belenko"}, {"given"=>"Frank", "family"=>"Sun"}, {"given"=>"Minsik", "family"=>"Cho"}, {"given"=>"Mohammad", "family"=>"Hossein Sekhavat"}, {"given"=>"Moin", "family"=>"Nabi"}, {"given"=>"Mehrdad", "family"=>"Farajtabar"}]Text Summarization With Graph Attention Networks2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/ardestani24a[{"given"=>"Mohammadreza", "family"=>"Ardestani"}, {"given"=>"Yllias", "family"=>"Chali"}]Computational Bottlenecks of Training Small-scale Large Language Models2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/ashkboos24a[{"given"=>"Saleh", "family"=>"Ashkboos"}, {"given"=>"Seyed", "family"=>"Iman Mirzadeh"}, {"given"=>"Keivan", "family"=>"Alizadeh-Vahid"}, {"given"=>"Mohammad", "family"=>"Hossein Sekhavat"}, {"given"=>"Moin", "family"=>"Nabi"}, {"given"=>"Mehrdad", "family"=>"Farajtabar"}, {"given"=>"Fartash", "family"=>"Faghri"}]KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/azimi24a[{"given"=>"Rambod", "family"=>"Azimi"}, {"given"=>"Rishav", "family"=>"Rishav"}, {"given"=>"Marek", "family"=>"Teichmann"}, {"given"=>"Samira", "family"=>"Ebrahimi Kahou"}]Speculative Streaming: Fast LLM Inference without Auxiliary Models2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/bhendawade24a[{"given"=>"Nikhil", "family"=>"Bhendawade"}, {"given"=>"Irina", "family"=>"Belousova"}, {"given"=>"Qichen", "family"=>"Fu"}, {"given"=>"Henry", "family"=>"Mason"}, {"given"=>"Mohammad", "family"=>"Rastegari"}, {"given"=>"Mahyar", "family"=>"Najibi"}]OnlySportsLM: Optimizing Sports-Domain Language Models with SOTA Performance under Billion Parameters2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/chen24a[{"given"=>"Zexin", "family"=>"Chen"}, {"given"=>"Chengxi", "family"=>"Li"}, {"given"=>"Xiangyu", "family"=>"Xie"}, {"given"=>"Parijat", "family"=>"Dube"}]Beyond Parameter Count: Implicit Bias in Soft Mixture of Experts2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/chung24a[{"given"=>"Youngseog", "family"=>"Chung"}, {"given"=>"Dhruv", "family"=>"Malik"}, {"given"=>"Jeff", "family"=>"Schneider"}, {"given"=>"Yuanzhi", "family"=>"Li"}, {"given"=>"Aarti", "family"=>"Singh"}]Mai Ho‘omāuna i ka ‘Ai: Language Models Improve Automatic Speech Recognition in Hawaiian2024-12-10T00:00:00+00:002024-12-10T00:00:00+00:00https://proceedings.mlr.press/v262/d-chaparala24a[{"given"=>"Kaavya", "family"=>"D Chaparala"}, {"given"=>"Guido", "family"=>"Zarrella"}, {"given"=>"Bruce", "family"=>"Torres Fischer"}, {"given"=>"Larry", "family"=>"Kimura"}, {"given"=>"Oiwi", "family"=>"Parker Jones"}]