3 papers
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…
cs.LG2025
Sparsified State-Space Models are Efficient Highway Networks
Woomin Song, Jihoon Tack, Sangwoo Mo +2
State-space models (SSMs) offer a promising architecture for sequence modeling, providing an alternative to Transformers by replacing expensive self-attention with linear recurrenc…
cs.LG2025
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification
Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim +2
Self-awareness, i.e., the ability to assess and correct one's own generation, is a fundamental aspect of human intelligence, making its replication in large language models (LLMs)…