影响力指数

11.21/100

超过 34.8%

全站排名 #41,993

发表论文3 篇

平均评分3.7

年均产出3.0 篇/年

Anisha Gunjal

Researcher@Scale AI·美国·OpenReview

研究方向

nlp · deep learning · grounded nlp

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains

ICLR 2026Poster

Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models

ICLR 2026Withdrawn

TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models

ICLR 2026Withdrawn

合作者 (19)

Sean M. Hendryx

Chen Bo Calvin Zhang