影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
49.14/100
前 9%
全站排名 #5,799
发表论文12 篇
平均评分
年均产出4.0 篇/年
Jason Xue
研究方向
Critical infrastructure resilience and protection · Federated learning · Responsible AI · AI security · privacy · and safety · System security and privacy · Trustworthy AI · Mobile security and privacy · Software security · Internet measurement
20
Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
ICLR 2026Desk Rejected
21
ReTrace: Reinforcement Learning-Guided Reconstruction Attacks on Machine Unlearning
ICLR 2026Poster
三作15
Adaptive Rank, Reduced Forgetting: Knowledge Retention in Continual Learning Vision-Language Models with Dynamic Rank-Selective LoRA
ICLR 2026Rejected
三作19
Little By Little: Continual Learning via Self-Activated Sparse Mixture-of-Rank Adaptive Learning
ICLR 2026Rejected
三作18
Adaptive Gray: Reducing Color Dependency to Improve Generalization in Deepfake Detection
ICLR 2026Rejected
20
ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models
NeurIPS 2025Poster
24
One Head to Rule Them All: Amplifying LVLM Safety through a Single Critical Attention Head
NeurIPS 2025Poster
通讯22
E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
NeurIPS 2025Poster