Dylan J Foster
~Dylan_J_Foster1
12
论文总数
6.0
年均投稿
平均评分
接收情况12/12
会议分布
NeurIPS
6
ICLR
5
ICML
1
发表论文 (12 篇)
20254 篇
4
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
ICLR 2025Poster
4
Self-Improvement in Language Models: The Sharpening Mechanism
ICLR 2025Oral
4
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
ICML 2025Poster
5
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
ICLR 2025Spotlight
20248 篇
4
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
NeurIPS 2024Spotlight
4
Online Estimation via Offline Estimation: An Information-Theoretic Framework
NeurIPS 2024Poster
4
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
NeurIPS 2024Spotlight
4
The Power of Resets in Online Reinforcement Learning
NeurIPS 2024Spotlight
3
Harnessing Density Ratios for Online Reinforcement Learning
ICLR 2024Spotlight
3
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
ICLR 2024Poster
3
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
NeurIPS 2024Oral
4
Can large language models explore in-context?
NeurIPS 2024Poster