影响力指数

35.93/100

前 17.9%

全站排名 #11,533

发表论文3 篇

平均评分6.6

年均产出1.5 篇/年

Satvik Golechha

Researcher@Independent·美国·OpenReview

ABBEL: LLM Agents Acting Through Belief Bottlenecks Expressed in Language

ICLR 2026Rejected

Among Us: A Sandbox for Measuring and Detecting Agentic Deception

NeurIPS 2025Spotlight

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

NeurIPS 2025Oral

合作者 (10)

Jakob Brandt Bjorner

Hardik Bhatnagar

James Wilken-Smith

Joseph Isaac Bloom