Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding
Alexander Samarin, Sergei Krutikov, Anton Shevtsov +3
Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parall…
cs.LG2026
SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding
Anton Plaksin, Sergei Krutikov, Sergei Skvortsov +1
Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model proposes tokens which the tar…
cs.LG2025
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
Alexander Golubev, Maria Trofimova, Sergei Polezhaev +9
Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code…