Yuxin Chen

papers

1,748

total citations

papers (26)

Channel-Wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition

ICCV 2021arXiv

798

citations

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model

NEURIPS 2020arXiv

143

citations

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction

NEURIPS 2020arXiv

131

citations

Taming Rectified Flow for Inversion and Editing

ICML 2025arXiv

119

citations

Open-Vocabulary One-Stage Detection With Hierarchical Visual-Language Knowledge Distillation

CVPR 2022arXiv

104

citations

Wukong: Towards a Scaling Law for Large-Scale Recommendation

ICML 2024arXiv

citations

Accelerating Convergence of Score-Based Diffusion Models, Provably

ICML 2024arXiv

citations

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning

NEURIPS 2021arXiv

citations

Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context

ICML 2024arXiv

citations

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

NEURIPS 2023arXiv

citations

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

NEURIPS 2021arXiv

citations

Language Representations Can be What Recommenders Need: Findings and Potentials

ICLR 2025arXiv

citations

Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model

NEURIPS 2022arXiv

citations

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

NEURIPS 2023arXiv

citations

Teaching an Active Learner with Contrastive Examples

NEURIPS 2021arXiv

citations

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

NEURIPS 2025arXiv

citations

Designing Specialized Two-Dimensional Graph Spectral Filters for Spatial-Temporal Graph Modeling

AAAI 2025

citations

VisionMath: Vision-Form Mathematical Problem-Solving

ICCV 2025

citations

Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm

NEURIPS 2021

citations

Yuxin Chen

papers (26)

Channel-Wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction

Taming Rectified Flow for Inversion and Editing

Open-Vocabulary One-Stage Detection With Hierarchical Visual-Language Knowledge Distillation

Wukong: Towards a Scaling Law for Large-Scale Recommendation

Accelerating Convergence of Score-Based Diffusion Models, Provably

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning

Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

Language Representations Can be What Recommenders Need: Findings and Potentials

Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

Teaching an Active Learner with Contrastive Examples

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?

Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion

DOGR: Towards Versatile Visual Document Grounding and Referring

Riemannian Consistency Model

Mamba-3VL: Taming State Space Model for 3D Vision Language Learning

ViLEM: Visual-Language Error Modeling for Image-Text Retrieval

Order-Prompted Tag Sequence Generation for Video Tagging

Designing Specialized Two-Dimensional Graph Spectral Filters for Spatial-Temporal Graph Modeling

VisionMath: Vision-Form Mathematical Problem-Solving

Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm

papers (26)

Channel-Wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction

Taming Rectified Flow for Inversion and Editing

Open-Vocabulary One-Stage Detection With Hierarchical Visual-Language Knowledge Distillation

Wukong: Towards a Scaling Law for Large-Scale Recommendation

Accelerating Convergence of Score-Based Diffusion Models, Provably

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning

Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

Language Representations Can be What Recommenders Need: Findings and Potentials

Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

Teaching an Active Learner with Contrastive Examples

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?

Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion

DOGR: Towards Versatile Visual Document Grounding and Referring

Riemannian Consistency Model

Mamba-3VL: Taming State Space Model for 3D Vision Language Learning

ViLEM: Visual-Language Error Modeling for Image-Text Retrieval

Order-Prompted Tag Sequence Generation for Video Tagging

Designing Specialized Two-Dimensional Graph Spectral Filters for Spatial-Temporal Graph Modeling

VisionMath: Vision-Form Mathematical Problem-Solving

Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm