← Search

Roman Garipov

2 accepted papers

2025

AutoJudge: Judge Decoding Without Manual Annotation

NeurIPS 2025poster

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 distribution token-by-token, we identify the generated tokens that affect the downstream quality of the response, relax…

Cited by 0SourceScholar
2025

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

NeurIPS 2025spotlight

Large Language Models (LLMs) have demonstrated the ability to tackle increasingly complex tasks through advanced reasoning, long-form content generation, and tool use. Solving these tasks often involves long inference-time computations. In human problem solving, a common strategy to expedite work is…

Cited by 0SourcecodeScholar