影响力指数

52.1/100

前 7.5%

全站排名 #4,842

发表论文4 篇

平均评分7.5

年均产出2.0 篇/年

Julian Minder

PhD student@EPFL - EPF Lausanne·瑞士·OpenReview

研究方向

NLP · Interpretability

Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences

ICLR 2026Poster

The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?

NeurIPS 2025Spotlight

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning

NeurIPS 2025Poster

Controllable Context Sensitivity and the Knob Behind It

ICLR 2025Poster

合作者 (16)

博士导师2 篇

博士导师1 篇