Gen Li

papers

1,624

total citations

papers (23)

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

CVPR 2021arXiv

464

citations

VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

ECCV 2022arXiv

171

citations

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

ICML 2024arXiv

152

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

Accelerating Convergence of Score-Based Diffusion Models, Provably

ICML 2024arXiv

citations

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding

CVPR 2023arXiv

citations

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

NEURIPS 2021arXiv

citations

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

ICCV 2025arXiv

citations

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

NEURIPS 2023arXiv

citations

One-Shot Open Affordance Learning with Foundation Models

CVPR 2024arXiv

citations

OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer

CVPR 2023arXiv

citations

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

NEURIPS 2021arXiv

citations

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

CVPR 2023arXiv

citations

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

NEURIPS 2023arXiv

citations

Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal

AAAI 2024arXiv

citations

Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time

NEURIPS 2023arXiv

citations

EgoM2P: Egocentric Multimodal Multitask Pretraining

ICCV 2025arXiv

citations

VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions

ICCV 2025arXiv

citations

Advancing Dynamic Sparse Training by Exploring Optimization Opportunities

ICML 2024

citations

Gen Li

papers (23)

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

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

Accelerating Convergence of Score-Based Diffusion Models, Provably

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding

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

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

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

One-Shot Open Affordance Learning with Foundation Models

OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer

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

Dynamic Sparsity Is Channel-Level Sparsity Learner

EgoGen: An Egocentric Synthetic Data Generator

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

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

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

Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal

Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time

EgoM2P: Egocentric Multimodal Multitask Pretraining

VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions

Advancing Dynamic Sparse Training by Exploring Optimization Opportunities

papers (23)

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

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

Accelerating Convergence of Score-Based Diffusion Models, Provably

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding

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

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

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

One-Shot Open Affordance Learning with Foundation Models

OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer

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

Dynamic Sparsity Is Channel-Level Sparsity Learner

EgoGen: An Egocentric Synthetic Data Generator

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

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

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

Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal

Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time

EgoM2P: Egocentric Multimodal Multitask Pretraining

VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions

Advancing Dynamic Sparse Training by Exploring Optimization Opportunities