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
56.82/100
前 5.8%
全站排名 #3,713
发表论文15 篇
平均评分
年均产出5.0 篇/年
Yang Zhou
研究方向
Natural Language Processing · Machine Learning · Parallel and Distributed Computing · Trustworthy Machine Learning
33
Automatic Dialectic Jailbreak: A Framework for Generating Effective Jailbreak Strategies
ICLR 2026Poster
二作21
Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss
ICLR 2026Poster
29
Stealthy Jailbreaking Attacks via Hyperbolic Hamiltonian Dynamics and Möbius Fusion
ICLR 2026Rejected
二作13
Adversarial Advertisement in Text-to-Image Generative Models
ICLR 2026Rejected
二作4
Expectation–Evidence Prompting: Structuring Verification by Comparing Expected and Observed Evidence
ICLR 2026Withdrawn
通讯24
On Training Mixture-of-Experts: A Social Choice Perspective
ICLR 2026Rejected
25
Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
NeurIPS 2025Spotlight
通讯12
Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning
ICML 2025Poster
二作25
PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders
NeurIPS 2025Poster
通讯25
On PAC-Bayes Bounds for Linear Autoencoders
ICLR 2025Rejected
通讯15
PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders
ICML 2025Rejected
通讯6
k-Odd One Clear (k-OOC), a novel GPU kernel that improves quantization accuracy and speed of GPTQ algorithm
ICLR 2025Withdrawn
51
Riemannian Low-Rank Adaptation for Federated Fine-Tuning of Foundation Models
ICLR 2025Withdrawn
二作