影响力指数

-/100

发表论文2 篇

平均评分4.3

年均产出1.0 篇/年

TianlangXue

Intern@The Hong Kong University of Science and Technology·中国·OpenReview

Attention Smoothing: Correcting Causal Bias in Autoregressive Language Models

ICLR 2026Rejected

CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models

ICLR 2025Rejected

合作者 (13)