Comprehensive Reinforcement Learning Framework for Atari and MuJoCo
This project implements a comprehensive Reinforcement Learning framework capable of solving both discrete control tasks (Atari games using DQN) and continuous control tasks (MuJoCo robotics using PPO). It is designed for modularity, scalability, and ease of experimentation, featuring automated parallel training, configuration-driven evaluation, and robust headless visualization support.
Jan 18, 2026
Model Merging Overview
Please refer to this ariticle for details.
Aug 22, 2025
🎙️ Auto Speech Recognition
I dove into the world of Automatic Speech Recognition (ASR) by building a Large Vocabulary Continuous Speech Recognition (LVCSR) system using the Kaldi toolkit.
Jun 25, 2025
🧩 ViT on CIFAR-10
This project is a complete implementation of Vision Transformer (ViT) applied to small-scale datasets (especially CIFAR-10), including extensive exploration.
May 31, 2025
🎙️ Voice Activity Detection
I conducted extensive experiments comparing frame division methods and model performances, with rich visualizations.
May 15, 2025