Name: HE LE
Type: User
Company: Guangzhou University
Bio: A master student pursuing his master's degree.
research interests include Deep Learning, Neural ODE, Bayesian Learning and MIMO detection.
Location: Guangzhou
Blog: https://github.com/runwuxisilence
HE LE's Projects
Pytorch implementation of Augmented Neural ODEs :sunflower:
A collection of resources regarding the interplay between differential equations, deep learning, dynamical systems, control and numerical methods.
Awesome resources on normalizing flows.
Crowdfunding open source projects: use OpenReview's high-quality review data to fine-tune a professional review and response LLM. 众筹开源项目:利用OpenReview的优质审稿数据,微调出一个专业的审稿和审稿回复GPT
Digital Communication with Python
Denoising Diffusion Probabilistic Models
Elucidating the Design Space of Diffusion-Based Generative Models (EDM)
code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".
Code for the paper "Language Models are Unsupervised Multitask Learners"
为GPT/GLM等基座大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
强化学习玩超级马里奥
Code for ICML 2023 paper, "PFGM++: Unlocking the Potential of Physics-Inspired Generative Models"
An implementation of (Double/Dueling) Deep-Q Learning to play Super Mario Bros.
Code for NeurIPS 2022 Paper, "Poisson Flow Generative Models" (PFGM)
Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros
DQN model used to train and beat Super Mario Bros. for the NES using PyTorch
This project explores deep reinforcement learning, hybrid actor-critic approach with A3C/PPO combined with curiosity for playing Super Mario Bros
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
A Tutorial of Thompson Sampling