3 papers
cs.CL2026
Contextual Correction of Parallel Drafts for Speculative Decoding
Roy Eisenstadt, Harel Lidar, Tal Gonen +5
Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target m…
cs.CL2025
Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models
Omer Luxembourg, Haim Permuter, Eliya Nachmani
Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore inte…
cs.IT2024
TREET: TRansfer Entropy Estimation via Transformers
Omer Luxembourg, Dor Tsur, Haim Permuter
Transfer entropy (TE) is an information theoretic measure that reveals the directional flow of information between processes, providing valuable insights for a wide range of real-w…