Picture for Wei-Fang Sun

Wei-Fang Sun

Retraining-Free Merging of Sparse Mixture-of-Experts via Hierarchical Clustering

Add code
Oct 11, 2024
Viaarxiv icon

Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow

Add code
May 22, 2024
Viaarxiv icon

DriveEnv-NeRF: Exploration of A NeRF-Based Autonomous Driving Environment for Real-World Performance Validation

Add code
Mar 23, 2024
Viaarxiv icon

Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning

Add code
Feb 01, 2024
Viaarxiv icon

A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning

Add code
Jun 04, 2023
Viaarxiv icon

Training Energy-Based Normalizing Flow with Score-Matching Objectives

Add code
May 24, 2023
Viaarxiv icon

Quasi-Conservative Score-based Generative Models

Add code
Sep 26, 2022
Figure 1 for Quasi-Conservative Score-based Generative Models
Figure 2 for Quasi-Conservative Score-based Generative Models
Figure 3 for Quasi-Conservative Score-based Generative Models
Figure 4 for Quasi-Conservative Score-based Generative Models
Viaarxiv icon

Denoising Likelihood Score Matching for Conditional Score-based Data Generation

Add code
Mar 27, 2022
Figure 1 for Denoising Likelihood Score Matching for Conditional Score-based Data Generation
Figure 2 for Denoising Likelihood Score Matching for Conditional Score-based Data Generation
Figure 3 for Denoising Likelihood Score Matching for Conditional Score-based Data Generation
Figure 4 for Denoising Likelihood Score Matching for Conditional Score-based Data Generation
Viaarxiv icon

DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

Add code
Feb 16, 2021
Figure 1 for DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
Figure 2 for DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
Figure 3 for DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
Figure 4 for DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
Viaarxiv icon