Tianyi Chen

papers

595

total citations

papers (27)

Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance

NEURIPS 2023arXiv

citations

Efficient Online Reinforcement Learning for Diffusion Policy

ICML 2025arXiv

citations

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF

ICML 2024arXiv

citations

A Single-timescale Analysis for Stochastic Approximation with Multiple Coupled Sequences

NEURIPS 2022arXiv

citations

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

ICML 2025arXiv

citations

Understanding Benign Overfitting in Gradient-Based Meta Learning

NEURIPS 2022arXiv

citations

DREAM: Diffusion Rectification and Estimation-Adaptive Models

CVPR 2024arXiv

citations

AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing

CVPR 2024arXiv

citations

AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models

CVPR 2025arXiv

citations

Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression

CVPR 2025arXiv

citations

Enhancing Robot Program Synthesis Through Environmental Context

NEURIPS 2023arXiv

citations

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning

ICML 2024arXiv

citations

ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents

NEURIPS 2025arXiv

citations

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

NEURIPS 2025arXiv

citations

SpotDiff: Spatial Gene Expression Imputation Diffusion with Single-Cell RNA Sequencing Data Integration

AAAI 2025

citations

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data

NEURIPS 2025arXiv

citations

Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis

CVPR 2023

citations

Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis

CVPR 2021

citations

An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition

NEURIPS 2023

citations

Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems

NEURIPS 2021

citations

Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation

ICCV 2021

citations

SphericGAN: Semi-Supervised Hyper-Spherical Generative Adversarial Networks for Fine-Grained Image Synthesis

CVPR 2022

citations

RetouchFormer: Semi-supervised High-Quality Face Retouching Transformer with Prior-Based Selective Self-Attention

AAAI 2024

citations

3DHumanEdit: Multi-modal Body Part-aware Conditioning Information Integration for 3D Human Manipulation

AAAI 2025

citations

Tianyi Chen

papers (27)

CAFE: Catastrophic Data Leakage in Vertical Federated Learning

Only Train Once: A One-Shot Neural Network Training And Pruning Framework

DistiLLM: Towards Streamlined Distillation for Large Language Models

Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance

Efficient Online Reinforcement Learning for Diffusion Policy

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF

A Single-timescale Analysis for Stochastic Approximation with Multiple Coupled Sequences

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Understanding Benign Overfitting in Gradient-Based Meta Learning

DREAM: Diffusion Rectification and Estimation-Adaptive Models

AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing

AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models

Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression

Enhancing Robot Program Synthesis Through Environmental Context

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning

ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

SpotDiff: Spatial Gene Expression Imputation Diffusion with Single-Cell RNA Sequencing Data Integration

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data

Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis

Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis

An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition

Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems

Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation

SphericGAN: Semi-Supervised Hyper-Spherical Generative Adversarial Networks for Fine-Grained Image Synthesis

RetouchFormer: Semi-supervised High-Quality Face Retouching Transformer with Prior-Based Selective Self-Attention

3DHumanEdit: Multi-modal Body Part-aware Conditioning Information Integration for 3D Human Manipulation

papers (27)

CAFE: Catastrophic Data Leakage in Vertical Federated Learning

Only Train Once: A One-Shot Neural Network Training And Pruning Framework

DistiLLM: Towards Streamlined Distillation for Large Language Models

Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance

Efficient Online Reinforcement Learning for Diffusion Policy

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF

A Single-timescale Analysis for Stochastic Approximation with Multiple Coupled Sequences

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Understanding Benign Overfitting in Gradient-Based Meta Learning

DREAM: Diffusion Rectification and Estimation-Adaptive Models

AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing

AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models

Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression

Enhancing Robot Program Synthesis Through Environmental Context

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning

ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

SpotDiff: Spatial Gene Expression Imputation Diffusion with Single-Cell RNA Sequencing Data Integration

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data

Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis

Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis

An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition

Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems

Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation

SphericGAN: Semi-Supervised Hyper-Spherical Generative Adversarial Networks for Fine-Grained Image Synthesis

RetouchFormer: Semi-supervised High-Quality Face Retouching Transformer with Prior-Based Selective Self-Attention

3DHumanEdit: Multi-modal Body Part-aware Conditioning Information Integration for 3D Human Manipulation