Full Project List

Making Artificial Motor Cortex

Creating artificial motor cortex by imitating naturalistic agents and performing generative inverse kinematics.

Deep Reinforcement Learning Imitation Learning Parallel Training

Seeing the Boundaries: Topological Clustering of Behavioral Primitives and Transitions

Studying latent space compression and stereotypical behavioral basis.

Computational Topology Representation Learning Segmentation

Dynamic Model for Planning Biomechanically Realistic Behaviors

Building planning & generation models with deep state space models.

Deep State Space Model Generative Model Long Horizon Planning

Motif-preserving Graph Tokenization for Biological Structure Generation

Designing a motif-preserve graph tokenization scheme, allowing sequence transformers to model long-range graph topology more effectively and generate biological graphs more accurately.

Graph Learning & Generation Motif Learning

Multimodal Model Embodied Simulation

Reverse engineering from a embodied language model's perspective.

MLLM Probing LLM-ology

Agent-based Multi-collaboration Framework

Farmework for tackling language model multi-agents collborations in an adversarial environment.

Multi-agent Inference System Cooperative/Adversarial Learning

Learn From Your Enemy

Full end-to-end A-MARL framework for competitive and cooperative AI training.

Deep Reinforcement Learning RL Environment Adversarial MARL

Latent Planning as Optimization

Learning is about how to create structured projection space and plan with it during post-training inference.

Data Efficient Sampling Offline Learning Long Horizon Planning

Data & Topological Driven Perspective Towards Stress & Rumination

Leveraging the power of neural network & topological data analysis to study the effect of stress & ruminations.

Topological Analysis Computational Neuroscience

Personalized Database For Study Data

Building a numerical and text database for my personal study data at UCSD to examine different study habits.

Data Science Workflow Vectorized Database & Language Model

Recommendation Systems for Business Owners

Building recommendation systems using sequential data for business owners.

Recommendation Systems Data Science Workflow Deep Learning

Robust Ensemble Learning

Ensemble learning in highly imbalanced real-world datasets.

Data Science Workflow Machine Learning

Multi-addicted State Q-agent Decision Making

Studying effects of addition computationally via discrete reinforcement learning.

Discrete Reinforcement Learning Computational Neuroscience

Laplacian Eigenmap Visualization

Intuitive visualization of dimensional reduction algorithm for educational purpose.

Educational Visualization Unsupervised Learning