3 papers
cs.LG2026
Reasoning Shift: How Context Silently Shortens LLM Reasoning
Gleb Rodionov, Roman Garipov, George Yakushev
Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, lo…
cs.CL2025
AutoJudge: Judge Decoding Without Manual Annotation
Roman Garipov, Fedor Velikonivtsev, Ivan Ermakov +3
We introduce AutoJudge, a method that accelerates large language model (LLM) inference with task-specific lossy speculative decoding. Instead of matching the original model output…
cs.LG2025
Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
Gleb Rodionov, Roman Garipov, Alina Shutova +6
Large Language Models (LLMs) have demonstrated the ability to tackle increasingly complex tasks through advanced reasoning, long-form content generation, and tool use. Solving thes…