Summary of Exploring and Improving Drafts in Blockwise Parallel Decoding, by Taehyeon Kim et al.
Exploring and Improving Drafts in Blockwise Parallel Decodingby Taehyeon Kim, Ananda Theertha Suresh, Kishore Papineni,…
Exploring and Improving Drafts in Blockwise Parallel Decodingby Taehyeon Kim, Ananda Theertha Suresh, Kishore Papineni,…
Extending Mean-Field Variational Inference via Entropic Regularization: Theory and Computationby Bohan Wu, David BleiFirst submitted…
Experimental Design for Active Transductive Inference in Large Language Modelsby Subhojyoti Mukherjee, Anusha Lalitha, Aniket…
On Speculative Decoding for Multimodal Large Language Modelsby Mukul Gagrani, Raghavv Goel, Wonseok Jeon, Junyoung…
CATS: Contextually-Aware Thresholding for Sparsity in Large Language Modelsby Donghyun Lee, Je-Yong Lee, Genghan Zhang,…
Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatchby Malek Mechergui, Sarath SreedharanFirst…
Convergence of coordinate ascent variational inference for log-concave measures via optimal transportby Manuel Arnese, Daniel…
Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decodingby Jie Ou, Yueming Chen,…
Seismic First Break Picking in a Higher Dimension Using Deep Graph Learningby Hongtao Wang, Li…
AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guaranteesby William Fleshman, Aleem Khan,…