影响力指数

54.84/100

前 6.5%

全站排名 #4,204

发表论文12 篇

平均评分5.7

年均产出4.0 篇/年

Weisen Jiang

Researcher@The Chinese University of Hong Kong·中国香港·OpenReview

研究方向

large language models · meta-learning

HarmoMoE: Unifying Domain-Specialized Experts into a Mixture-of-Experts Model under Privacy Constraints

ICLR 2026Rejected

SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance–Diversity Data Selection

ICLR 2026Rejected

MetaDefense: Defending Fine-tuning based Jailbreak Attack Before and During Generation

NeurIPS 2025Poster

Enhancing Pruned Models by Input Compensation

ICML 2025Rejected

PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model

ICML 2025Poster

Input Compensation for Pruned Models

ICLR 2025Rejected

合作者 (20)

博士导师9 篇

Sinno Jialin Pan

博后导师2 篇