影响力指数

39.75/100

前 14.6%

全站排名 #9,393

发表论文4 篇

平均评分6.2

年均产出1.3 篇/年

Raphaël Avalos

PhD student@Vrije Universiteit Brussel·比利时·OpenReview

研究方向

reinforcement learning · deep learning · llm · planning

Deep SPI: Safe Policy Improvement via World Models

ICLR 2026Poster

ShiQ: Bringing back Bellman to LLMs

NeurIPS 2025Poster

Sample, Predict, then Proceed: Self-Verification Sampling for Tool Use of LLMs

NeurIPS 2025Rejected

合作者 (16)

Florent Delgrange

Omar Darwiche Domingues

Aaron Courville

Diederik M Roijers

博士导师1 篇