影响力指数

39.41/100

前 14.8%

全站排名 #9,553

发表论文6 篇

平均评分5.5

年均产出2.0 篇/年

Vaskar Nath

Researcher@Scale AI·美国·OpenReview

Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models

ICLR 2026Withdrawn

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains

ICLR 2026Poster

Planning in Natural Language Improves LLM Search for Code Generation

ICLR 2025Spotlight

Revisiting the Superficial Alignment Hypothesis

ICLR 2025Rejected

ToolComp: A Multi-Tool Reasoning & Process Supervision Benchmark

ICLR 2025Rejected

合作者 (20)

Sean M. Hendryx

Federico Cassano