影响力指数

43.27/100

前 12.1%

全站排名 #7,810

发表论文6 篇

平均评分5.7

年均产出2.0 篇/年

Oleksii Kuchaiev

Principal Researcher@NVIDIA·美国·OpenReview

研究方向

Post-training · Large Language Models · Artificial Intelligence

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards

ICLR 2026Poster

Think Twice: Branch-and-Rethink Reasoning Reward Model

ICLR 2026Rejected

Adversarial Training of Reward Models

COLM 2025Poster

HelpSteer2-Preference: Complementing Ratings with Preferences

ICLR 2025Poster

LLM Pruning and Distillation in Practice

ICLR 2025Rejected

合作者 (20)

Olivier Delalleau

Alexander Bukharin