Jason D. Lee
~Jason_D._Lee1
41
论文总数
20.5
年均投稿
平均评分
接收情况32/41
会议分布
ICLR
24
NeurIPS
13
ICML
4
发表论文 (41 篇)
202525 篇
3
Understanding Factual Recall in Transformers via Associative Memories
ICLR 2025Spotlight
4
Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis
NeurIPS 2025Poster
3
Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis
ICLR 2025Rejected
4
The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models
NeurIPS 2025Spotlight
3
Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought
ICLR 2025Spotlight
4
Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
ICML 2025Poster
4
Deployment Efficient Reward-Free Exploration with Linear Function Approximation
NeurIPS 2025Poster
4
Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow
ICLR 2025Poster
6
Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
ICLR 2025Rejected
3
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
ICML 2025Poster
5
Learning Hierarchical Polynomials of Multiple Nonlinear Features
ICLR 2025Poster
4
Accelerating RL for LLM Reasoning with Optimal Advantage Regression
NeurIPS 2025Poster
4
Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank
ICLR 2025Poster
4
Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding
ICML 2025Poster
5
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
ICLR 2025Spotlight
4
Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
ICML 2025Poster
4
Emergence and scaling laws in SGD learning of shallow neural networks
NeurIPS 2025Poster
4
Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding
ICLR 2025Rejected
4
Deployment Efficient Reward-Free Exploration with Linear Function Approximation
ICLR 2025Rejected
5
What Makes a Reward Model a Good Teacher? An Optimization Perspective
NeurIPS 2025Spotlight
5
Understanding Optimization in Deep Learning with Central Flows
ICLR 2025Poster
4
Watermarking using Semantic-aware Speculative Sampling: from Theory to Practice
ICLR 2025Rejected
4
What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
NeurIPS 2025Spotlight
4
Task Diversity Shortens the ICL Plateau
ICLR 2025Rejected
4
Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
ICLR 2025Poster
202416 篇
4
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
NeurIPS 2024Poster
4
Horizon-Free Regret for Linear Markov Decision Processes
ICLR 2024Poster
5
Solving Robust MDPs through No-Regret Dynamics
ICLR 2024withdrawn
4
Learning Hierarchical Polynomials with Three-Layer Neural Networks
ICLR 2024Poster
5
Teaching Arithmetic to Small Transformers
ICLR 2024Poster
3
Reward Collapse in Aligning Large Language Models
ICLR 2024Rejected
4
Learning and Transferring Sparse Contextual Bigrams with Linear Transformers
NeurIPS 2024Poster
4
BitDelta: Your Fine-Tune May Only Be Worth One Bit
NeurIPS 2024Poster
4
Provable Reward-Agnostic Preference-Based Reinforcement Learning
ICLR 2024Spotlight
4
Provable Offline Preference-Based Reinforcement Learning
ICLR 2024Spotlight
5
Scaling Laws in Linear Regression: Compute, Parameters, and Data
NeurIPS 2024Poster
4
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity
NeurIPS 2024Poster
3
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
ICLR 2024Poster
-
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity
ICLR 2024withdrawn
4
Provably Efficient CVaR RL in Low-rank MDPs
ICLR 2024Poster
4
REBEL: Reinforcement Learning via Regressing Relative Rewards
NeurIPS 2024Poster