PaperHub
影响力指数
98.81/100
前 0.1%
全站排名 #23
发表论文47 篇
平均评分5.8
年均产出15.7 篇/年

Andreas Krause

Full Professor@ETH Zurich·瑞士·OpenReview
研究方向

reinforcement learning · Bayesian optimization · interactive machine learning · submodularity · gaussian processes · active learning

7.3
14

Safe Exploration via Policy Priors

ICLR 2026Poster
通讯
6.8
22

Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models

ICLR 2026Poster
6.5
16

Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game

ICLR 2026Poster
三作
6.5
15

Optimistic Task Inference for Behavior Foundation Models

ICLR 2026Oral
通讯
6.0
18

Thompson Sampling via Fine-Tuning of LLMs

ICLR 2026Poster
5.0
16

Verifier-Constrained Flow Expansion for Discovery Beyond the Data

ICLR 2026Poster
通讯
5.0
31

Learning Koopman Representations with Controllability Guarantees

ICLR 2026Poster
5.0
10

Efficient Generative Models Personalization via Optimal Experimental Design

ICLR 2026Desk Rejected
通讯
5.0
21

Test-time Offline Reinforcement Learning on Goal-related Experience

ICLR 2026Rejected
通讯
4.8
23

Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning

ICLR 2026Rejected
4.7
14

Reward-Guided Flow Merging via Implicit Density Operators

ICLR 2026Rejected
通讯
4.5
15

Sample-efficient and Scalable Exploration in Continuous-Time RL

ICLR 2026Poster
通讯
4.0
12

Constrained Generative Optimization via Progressive Flow Adaptation

ICLR 2026Rejected
通讯
4.0
19

Value Matching: Scalable and Gradient-Free Reward-Guided Flow Adaptation

ICLR 2026Poster
通讯
3.5
14

Enhancing Zero-Shot VLM Reward Models Through Structure-Aware Fine-Tuning

ICLR 2026Rejected
通讯
3.3
22

Making Offline Model-Based Reinforcement Learning Work on Real Robots

ICLR 2026Rejected
二作
8.2
20

DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning

NeurIPS 2025Poster
通讯
8.0
23

Composing Unbalanced Flows for Flexible Docking and Relaxation

ICLR 2025Oral
通讯
7.6
22

Residual Deep Gaussian Processes on Manifolds

ICLR 2025Oral
二作
7.0
15

Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs

ICLR 2025Poster
通讯
7.0
25

Standardizing Structural Causal Models

ICLR 2025Poster
通讯
6.8
27

Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning

NeurIPS 2025Spotlight
通讯
6.8
23

SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer

NeurIPS 2025Poster
通讯
6.8
34

MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization

ICLR 2025Poster
三作
6.8
24

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning

ICLR 2025Poster
通讯
6.4
20

SHAP values via sparse Fourier representation

NeurIPS 2025Spotlight
三作
6.3
17

Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging

COLM 2025Poster
通讯
6.1
11

Learning Safety Constraints for Large Language Models

ICML 2025Spotlight
三作
6.1
10

Provable Maximum Entropy Manifold Exploration via Diffusion Models

ICML 2025Poster
通讯
6.0
31

SOMBRL: Scalable and Optimistic Model-Based RL

NeurIPS 2025Poster
通讯
5.6
39

Amortized SHAP values via sparse Fourier function approximation

ICLR 2025Rejected
三作
5.5
11

Active Fine-Tuning of Multi-Task Policies

ICML 2025Poster
通讯
5.5
24

Active Fine-Tuning of Generalist Policies

ICLR 2025Rejected
通讯
5.5
23

Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design

ICLR 2025Poster
通讯
5.5
12

Generative Intervention Models for Causal Perturbation Modeling

ICML 2025Poster
通讯
4.5
5

Generative bandit optimization via diffusion posterior sampling

ICLR 2025Withdrawn
三作
合作者 (20)