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
70.36/100
前 2.6%
全站排名 #1,665
发表论文14 篇
平均评分
年均产出4.7 篇/年
Wojciech Samek
研究方向
federated learning · neural network compression · explainable AI · interpretable machine learning
22
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
ICLR 2026Poster
12
Attribution-Guided Decoding
ICLR 2026Poster
通讯18
Atlas-Alignment: Making Interpretability Transferable Across Language Models
ICLR 2026Rejected
通讯16
Circuit Insights: Towards Interpretability Beyond Activations
ICLR 2026Poster
15
ASIDE: Architectural Separation of Instructions and Data in Language Models
ICLR 2026Poster
14
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
ICLR 2026Poster
通讯18
Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
NeurIPS 2025Poster
22
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
ICLR 2025Poster
21
Fractional Diffusion Bridge Models
NeurIPS 2025Poster
通讯24
The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
NeurIPS 2025Poster
30
Synthetic Datasets for Machine Learning on Spatio-Temporal Graphs using PDEs
ICLR 2025Rejected
15
Inverse Engineering Diffusion: Deriving Variance Schedules with Rationale
ICLR 2025Rejected
三作