影响力指数

8.84/100

超过 27.6%

全站排名 #46,587

发表论文3 篇

平均评分4.9

年均产出1.5 篇/年

Hongzheng Yang

PhD student@The Chinese University of Hong Kong·中国·OpenReview

研究方向

Large Language Models · Safety alignment · deep learning

Concept Concentration for Faithful Representation Intervention

ICLR 2026Rejected

Scaling Language Model Reliability via Determinantal Point Process Prompt Sampling

ICLR 2026Rejected

SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning

ICML 2025Poster

合作者 (15)

Viet Anh Nguyen