Tim-Lin's repositories
mamba-in-depth
A comprehensive learning guide for understanding S4 (Structured State Space Sequence Model) and Mamba architectures, from fundamentals through implementation, with curated resources and hands-on examples.
drl-trading
Research on Deep Reinforcement Learning (DRL) for stock trading
multi-agent-ddpg
Implementation of MADDPG for cooperative-competitive multi-agent environments
nano-abnovo
Reproducing the core concepts from the paper "AbNovo: Constrained Preference Optimization for Multi-objective Antibody Design"
algorithm-implementation
python implementation for ai algorithm
neural-bio
A hybrid modeling framework combining neural networks with physics-based constraints for bioreactor process optimization and control.
reinforce-bio
Research on leveraging reinforcement learning to optimize bioprocess parameters and improve efficiency in biological systems.
agentic-ai-research
Exploring agentic AI systems: research, development, and insights.
antibody-bpe-tokenizer
A minimal BPE tokenizer trained from scratch for antibody heavy and light chain sequences.
data-science-hub
In-depth tutorials on data science, machine learning, statistics, and real-world analytics applications.
deepbiolab.github.io
DeepBioLab is an AI-focused platform designed to explore, build, and share advanced AI algorithms. It features educational content, projects, and research on topics like deep learning, reinforcement learning, and more. Dive into algorithms, develop from scratch, and discover solutions to science problems.
gans-research
🎨 A step-by-step implementation of key GAN architectures from Vanilla GAN to StyleGAN3, focusing on training stability, conditional control, and high-quality image generation.
gpt-bio
bioreactor modeling with autoregressive transformers for bioprocess optimization and simulation
gpt2-classification-peft
How to fine-tune a GPT-2 model for medical question-pair similarity tasks using Hugging Face's PEFT (Parameter-Efficient Fine-Tuning) library and LoRA (Low-Rank Adaptation)
healthbot
AI HealthBot Agent to provide personalized, on-demand patient education.
illustrated-alphazero
Implementation of AlphaZero, designed to demystify its core concepts and algorithms.
minimal-rl-vlm
A minimal implementation of PPO-based RL for vision-language models, designed to run on a single A100 GPU.
preparedness
Releases from OpenAI Preparedness
rag-for-proteins
A demonstration of Retrieval-Augmented Generation (RAG) applied to protein analysis
rendercv
The engine of the RenderCV App
TinyZero
Deepseek R1 zero tiny version own reproduce on two H100s on Hyperbolic Cloud
vlm-chart-interpreter
Train a vision language model from scratch used for chart interpretation in data analysis