Dylan Foster

Principal Researcher

论文与出版物

查看方式：

- Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
  
  Nived Rajaraman, Audrey Huang, Miro Dudík, Robert E. Schapire, Dylan Foster, Akshay Krishnamurthy
  
  March 2026
  
  Publication
- Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
  
  Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal, Carles Domingo-Enrich, Dylan Foster, Akshay Krishnamurthy
  
  March 2026
  
  Publication
- The Coverage Principle: How Pre-Training Enables Post-Training
  
  Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan T. Ash, Akshay Krishnamurthy, Akshay Krishnamurthy, Dylan J. Foster
  
  ICLR 2026 | October 2025
  
  Publication
- Representation-Based Exploration for Language Models: From Test-Time to Post-Training
  
  Jens Tuyls, Dylan Foster, Akshay Krishnamurthy, Jordan Ash
  
  ICLR 2026 | October 2025
  
  DOI Publication
- Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
  
  Dhruv Rohatgi, Abhishek Shetty, Donya Saless, Yuchen Li, Ankur Moitra, Andrej Risteski, Dylan Foster
  
  ICLR 2026 | October 2025
  
  DOI Publication
- Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
  
  Philip Amortila, Dylan Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
  
  NeurIPS 2024 | October 2024
  
  Publication
- The Power of Resets in Online Reinforcement Learning
  
  Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
  
  NeurIPS 2024 | October 2024
  
  Publication
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
  
  Dylan Foster, Adam Block, Dipendra Misra
  
  NeurIPS 2024 | July 2024
  
  DOI Publication Publication
- Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
  
  Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
  
  ICML 2024 | May 2024
  
  DOI
- Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
  
  Fan Chen, Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin, Yunbei Xu
  
  NeurIPS 2024 | May 2024
  
  Publication
- Online Estimation via Offline Estimation: An Information-Theoretic Framework
  
  Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin
  
  NeurIPS 2024 | April 2024
  
  DOI Publication Publication
- Can large language models explore in-context?
  
  Akshay Krishnamurthy, Keegan Harris, Dylan Foster, Cyril Zhang, Aleksandrs Slivkins
  
  NeurIPS 2024 | March 2024
  
  DOI Publication Publication
- Scalable Online Exploration via Coverability
  
  P. Amortila, Dylan Foster, Akshay Krishnamurthy
  
  ICML 2024 | March 2024
  
  DOI Publication Publication
- Harnessing Density Ratios for Online Reinforcement Learning
  
  P. Amortila, Dylan Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
  
  ICLR 2024 | January 2024
  
  DOI Publication
- Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
  
  Adam Block, Dylan Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
  
  ICLR 2024 | October 2023
  
  DOI Publication
- Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression
  
  Aleksandrs Slivkins (slivkins), Karthik Abinav Sankararaman, Dylan Foster
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory
  
  Andrew Wagenmaker, Dylan Foster
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Minimax Rates for Conditional Density Estimation via Empirical Entropy
  
  Blair Bilodeau, Dylan Foster, Daniel M. Roy
  
  Annals of Statistics | July 2023
  
  Publication
- On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
  
  Dylan Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient
  
  Dylan Foster, Noah Golowich, Yanjun Han
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
  
  Dylan Foster, Noah Golowich, Sham M. Kakade
  
  ICML 2023 | June 2023
  
  Publication
- The Role of Coverage in Online Reinforcement Learning
  
  Tengyang Xie, Dylan Foster, Yu Bai, Nan Jiang, Sham Kakade
  
  2023 International Conference on Learning Representations | May 2023
  
  Publication
- Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
  
  Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
  
  ICML 2023 | April 2023
  
  Publication
- Interaction-Grounded Learning with Action-Inclusive Feedback
  
  Tengyang Xie, Akanksha Saran, Dylan J Foster, Lekan P Molu, Ida Momennejad, Nan Jiang, Paul Mineiro, John Langford
  
  NeurIPS 2022 | November 2022
  
  Publication
- On the Complexity of Adversarial Decision Making
  
  Dylan J Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
  
  NeurIPS 2022 | November 2022
  
  Oral presentation
  
  Publication
- Understanding the Eluder Dimension
  
  Gene Li, Pritish Kamath, Dylan Foster, Nathan Srebro
  
  2022 Neural Information Processing Systems | October 2022
  
  Publication
- Contextual Bandits with Large Action Spaces: Made Practical
  
  Yinglun Zhu, Dylan Foster, John Langford, Paul Mineiro
  
  2022 International Conference on Machine Learning | July 2022
  
  Publication
- Lower Bounds for Non-Convex Stochastic Optimization
  
  Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan Foster, Nathan Srebro, Blake E. Woodworth
  
  Mathematical Programming | May 2022
  
  Publication Publication
- Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
  
  Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
  
  2022 Conference on Learning Theory | May 2022
  
  Publication
- Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
  
  Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
  
  2022 Conference on Learning Theory | May 2022
  
  Publication
- Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
  
  Dylan Foster, Akshay Krishnamurthy
  
  NeurIPS 2021 | December 2021
  
  Publication
- Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
  
  Dylan Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu
  
  2021 Conference on Learning Theory | July 2021
  
  Publication Publication Publication

- Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
  
  Nived Rajaraman, Audrey Huang, Miro Dudík, Robert E. Schapire, Dylan Foster, Akshay Krishnamurthy
  
  March 2026
  
  Publication
- Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
  
  Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal, Carles Domingo-Enrich, Dylan Foster, Akshay Krishnamurthy
  
  March 2026
  
  Publication
- The Coverage Principle: How Pre-Training Enables Post-Training
  
  Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan T. Ash, Akshay Krishnamurthy, Akshay Krishnamurthy, Dylan J. Foster
  
  ICLR 2026 | October 2025
  
  Publication
- Representation-Based Exploration for Language Models: From Test-Time to Post-Training
  
  Jens Tuyls, Dylan Foster, Akshay Krishnamurthy, Jordan Ash
  
  ICLR 2026 | October 2025
  
  DOI Publication
- Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
  
  Dhruv Rohatgi, Abhishek Shetty, Donya Saless, Yuchen Li, Ankur Moitra, Andrej Risteski, Dylan Foster
  
  ICLR 2026 | October 2025
  
  DOI Publication
- The Power of Resets in Online Reinforcement Learning
  
  Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
  
  NeurIPS 2024 | October 2024
  
  Publication
- Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
  
  Philip Amortila, Dylan Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
  
  NeurIPS 2024 | October 2024
  
  Publication
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
  
  Dylan Foster, Adam Block, Dipendra Misra
  
  NeurIPS 2024 | July 2024
  
  DOI Publication Publication
- Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
  
  Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
  
  ICML 2024 | May 2024
  
  DOI
- Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
  
  Fan Chen, Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin, Yunbei Xu
  
  NeurIPS 2024 | May 2024
  
  Publication
- Online Estimation via Offline Estimation: An Information-Theoretic Framework
  
  Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin
  
  NeurIPS 2024 | April 2024
  
  DOI Publication Publication
- Can large language models explore in-context?
  
  Akshay Krishnamurthy, Keegan Harris, Dylan Foster, Cyril Zhang, Aleksandrs Slivkins
  
  NeurIPS 2024 | March 2024
  
  DOI Publication Publication
- Scalable Online Exploration via Coverability
  
  P. Amortila, Dylan Foster, Akshay Krishnamurthy
  
  ICML 2024 | March 2024
  
  DOI Publication Publication
- Harnessing Density Ratios for Online Reinforcement Learning
  
  P. Amortila, Dylan Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
  
  ICLR 2024 | January 2024
  
  DOI Publication
- Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
  
  Adam Block, Dylan Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
  
  ICLR 2024 | October 2023
  
  DOI Publication
- Minimax Rates for Conditional Density Estimation via Empirical Entropy
  
  Blair Bilodeau, Dylan Foster, Daniel M. Roy
  
  Annals of Statistics | July 2023
  
  Publication
- On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
  
  Dylan Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression
  
  Aleksandrs Slivkins (slivkins), Karthik Abinav Sankararaman, Dylan Foster
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory
  
  Andrew Wagenmaker, Dylan Foster
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient
  
  Dylan Foster, Noah Golowich, Yanjun Han
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
  
  Dylan Foster, Noah Golowich, Sham M. Kakade
  
  ICML 2023 | June 2023
  
  Publication
- The Role of Coverage in Online Reinforcement Learning
  
  Tengyang Xie, Dylan Foster, Yu Bai, Nan Jiang, Sham Kakade
  
  2023 International Conference on Learning Representations | May 2023
  
  Publication
- Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
  
  Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
  
  ICML 2023 | April 2023
  
  Publication
- On the Complexity of Adversarial Decision Making
  
  Dylan J Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
  
  NeurIPS 2022 | November 2022
  
  Oral presentation
  
  Publication
- Interaction-Grounded Learning with Action-Inclusive Feedback
  
  Tengyang Xie, Akanksha Saran, Dylan J Foster, Lekan P Molu, Ida Momennejad, Nan Jiang, Paul Mineiro, John Langford
  
  NeurIPS 2022 | November 2022
  
  Publication
- Understanding the Eluder Dimension
  
  Gene Li, Pritish Kamath, Dylan Foster, Nathan Srebro
  
  2022 Neural Information Processing Systems | October 2022
  
  Publication
- Contextual Bandits with Large Action Spaces: Made Practical
  
  Yinglun Zhu, Dylan Foster, John Langford, Paul Mineiro
  
  2022 International Conference on Machine Learning | July 2022
  
  Publication
- Lower Bounds for Non-Convex Stochastic Optimization
  
  Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan Foster, Nathan Srebro, Blake E. Woodworth
  
  Mathematical Programming | May 2022
  
  Publication Publication
- Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
  
  Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
  
  2022 Conference on Learning Theory | May 2022
  
  Publication
- Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
  
  Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
  
  2022 Conference on Learning Theory | May 2022
  
  Publication
- Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
  
  Dylan Foster, Akshay Krishnamurthy
  
  NeurIPS 2021 | December 2021
  
  Publication
- Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
  
  Dylan Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu
  
  2021 Conference on Learning Theory | July 2021
  
  Publication Publication Publication
- Lower Bounds for Non-Convex Stochastic Optimization
  
  Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan Foster, Nathan Srebro, Blake E. Woodworth
  
  Mathematical Programming | May 2022
  
  Publication Publication
- Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
  
  Dylan Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu
  
  2021 Conference on Learning Theory | July 2021
  
  Publication Publication Publication

- Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
  
  Nived Rajaraman, Audrey Huang, Miro Dudík, Robert E. Schapire, Dylan Foster, Akshay Krishnamurthy
  
  March 2026
  
  Publication
- Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
  
  Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal, Carles Domingo-Enrich, Dylan Foster, Akshay Krishnamurthy
  
  March 2026
  
  Publication
- The Coverage Principle: How Pre-Training Enables Post-Training
  
  Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan T. Ash, Akshay Krishnamurthy, Akshay Krishnamurthy, Dylan J. Foster
  
  ICLR 2026 | October 2025
  
  Publication
- Representation-Based Exploration for Language Models: From Test-Time to Post-Training
  
  Jens Tuyls, Dylan Foster, Akshay Krishnamurthy, Jordan Ash
  
  ICLR 2026 | October 2025
  
  DOI Publication
- Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
  
  Dhruv Rohatgi, Abhishek Shetty, Donya Saless, Yuchen Li, Ankur Moitra, Andrej Risteski, Dylan Foster
  
  ICLR 2026 | October 2025
  
  DOI Publication
- The Power of Resets in Online Reinforcement Learning
  
  Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
  
  NeurIPS 2024 | October 2024
  
  Publication
- Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
  
  Philip Amortila, Dylan Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
  
  NeurIPS 2024 | October 2024
  
  Publication
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
  
  Dylan Foster, Adam Block, Dipendra Misra
  
  NeurIPS 2024 | July 2024
  
  DOI Publication Publication
- Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
  
  Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
  
  ICML 2024 | May 2024
  
  DOI
- Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
  
  Fan Chen, Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin, Yunbei Xu
  
  NeurIPS 2024 | May 2024
  
  Publication
- Online Estimation via Offline Estimation: An Information-Theoretic Framework
  
  Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin
  
  NeurIPS 2024 | April 2024
  
  DOI Publication Publication
- Can large language models explore in-context?
  
  Akshay Krishnamurthy, Keegan Harris, Dylan Foster, Cyril Zhang, Aleksandrs Slivkins
  
  NeurIPS 2024 | March 2024
  
  DOI Publication Publication
- Scalable Online Exploration via Coverability
  
  P. Amortila, Dylan Foster, Akshay Krishnamurthy
  
  ICML 2024 | March 2024
  
  DOI Publication Publication
- Harnessing Density Ratios for Online Reinforcement Learning
  
  P. Amortila, Dylan Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
  
  ICLR 2024 | January 2024
  
  DOI Publication
- Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
  
  Adam Block, Dylan Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
  
  ICLR 2024 | October 2023
  
  DOI Publication
- On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
  
  Dylan Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression
  
  Aleksandrs Slivkins (slivkins), Karthik Abinav Sankararaman, Dylan Foster
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory
  
  Andrew Wagenmaker, Dylan Foster
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient
  
  Dylan Foster, Noah Golowich, Yanjun Han
  
  2023 Conference on Learning Theory | July 2023
  
  Publication
- Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
  
  Dylan Foster, Noah Golowich, Sham M. Kakade
  
  ICML 2023 | June 2023
  
  Publication
- The Role of Coverage in Online Reinforcement Learning
  
  Tengyang Xie, Dylan Foster, Yu Bai, Nan Jiang, Sham Kakade
  
  2023 International Conference on Learning Representations | May 2023
  
  Publication
- Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
  
  Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
  
  ICML 2023 | April 2023
  
  Publication
- On the Complexity of Adversarial Decision Making
  
  Dylan J Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
  
  NeurIPS 2022 | November 2022
  
  Oral presentation
  
  Publication
- Interaction-Grounded Learning with Action-Inclusive Feedback
  
  Tengyang Xie, Akanksha Saran, Dylan J Foster, Lekan P Molu, Ida Momennejad, Nan Jiang, Paul Mineiro, John Langford
  
  NeurIPS 2022 | November 2022
  
  Publication
- Understanding the Eluder Dimension
  
  Gene Li, Pritish Kamath, Dylan Foster, Nathan Srebro
  
  2022 Neural Information Processing Systems | October 2022
  
  Publication
- Contextual Bandits with Large Action Spaces: Made Practical
  
  Yinglun Zhu, Dylan Foster, John Langford, Paul Mineiro
  
  2022 International Conference on Machine Learning | July 2022
  
  Publication
- Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
  
  Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
  
  2022 Conference on Learning Theory | May 2022
  
  Publication
- Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
  
  Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
  
  2022 Conference on Learning Theory | May 2022
  
  Publication
- Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
  
  Dylan Foster, Akshay Krishnamurthy
  
  NeurIPS 2021 | December 2021
  
  Publication
- Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
  
  Dylan Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu
  
  2021 Conference on Learning Theory | July 2021
  
  Publication Publication Publication
- Minimax Rates for Conditional Density Estimation via Empirical Entropy
  
  Blair Bilodeau, Dylan Foster, Daniel M. Roy
  
  Annals of Statistics | July 2023
  
  Publication
- Lower Bounds for Non-Convex Stochastic Optimization
  
  Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan Foster, Nathan Srebro, Blake E. Woodworth
  
  Mathematical Programming | May 2022
  
  Publication Publication

Dylan Foster

论文与出版物

Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference

The Coverage Principle: How Pre-Training Enables Post-Training

Representation-Based Exploration for Language Models: From Test-Time to Post-Training

Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking

Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity

The Power of Resets in Online Reinforcement Learning

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability

Online Estimation via Offline Estimation: An Information-Theoretic Framework

Can large language models explore in-context?

Scalable Online Exploration via Coverability

Harnessing Density Ratios for Online Reinforcement Learning

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression

Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory

Minimax Rates for Conditional Density Estimation via Empirical Entropy

On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring

Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient

Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games

The Role of Coverage in Online Reinforcement Learning

Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL

Interaction-Grounded Learning with Action-Inclusive Feedback

On the Complexity of Adversarial Decision Making

Understanding the Eluder Dimension

Contextual Bandits with Large Action Spaces: Made Practical

Lower Bounds for Non-Convex Stochastic Optimization

Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation

Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information

Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination

Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective

Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference

The Coverage Principle: How Pre-Training Enables Post-Training

Representation-Based Exploration for Language Models: From Test-Time to Post-Training

Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking

The Power of Resets in Online Reinforcement Learning

Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability

Online Estimation via Offline Estimation: An Information-Theoretic Framework

Can large language models explore in-context?

Scalable Online Exploration via Coverability

Harnessing Density Ratios for Online Reinforcement Learning

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Minimax Rates for Conditional Density Estimation via Empirical Entropy

On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring

Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression

Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory

Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient

Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games

The Role of Coverage in Online Reinforcement Learning

Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL

On the Complexity of Adversarial Decision Making

Interaction-Grounded Learning with Action-Inclusive Feedback

Understanding the Eluder Dimension

Contextual Bandits with Large Action Spaces: Made Practical

Lower Bounds for Non-Convex Stochastic Optimization

Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information

Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation

Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination

Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective

Lower Bounds for Non-Convex Stochastic Optimization

Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective

Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference

The Coverage Principle: How Pre-Training Enables Post-Training

Representation-Based Exploration for Language Models: From Test-Time to Post-Training

Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking

The Power of Resets in Online Reinforcement Learning

Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability

Online Estimation via Offline Estimation: An Information-Theoretic Framework

Can large language models explore in-context?