2 papers
cs.CL2025
Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers
Woomin Song, Sai Muralidhar Jayanthi, Srikanth Ronanki +5
As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has em…
cs.CL2025
Mamba Drafters for Speculative Decoding
Daewon Choi, Seunghyuk Oh, Saket Dingliwal +9
Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target mode…