Full Project List

Making Artificial Motor Cortex: Neuromechanical Emulation of Animal Behavior

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

Embodied Agents & RL Computational Neuroscience Deep Reinforcement Learning Imitation Learning Parallel Training

Shaped by What's Missing: Topological Discovery of Behavioral Transitions

Studying latent space compression and topological insights of motor control.

Representation & Topology Computational Neuroscience Computational Topology Representation Learning High-dimensional Reasoning

Beyond Flat Walks: Compositional Abstraction for Autoregressive Molecular Generation

Designing hiearchical tokenization scheme, allowing sequence transformers to model and genearte complex molecules better.

Generative Models Representation & Topology Graph Learning Graph Generation

Motor Decisions: Discrete Action Selection in a Virtual Rodent Predicts Neural Population Structure

Investigating how discrete action selection in virtual rodent models predicts neural population structure.

Embodied Agents & RL Computational Neuroscience Discrete Motor Control Neural Population

Propel: Structured Constraint Framework for Claude Code

A constraint framework enhancing Claude's effectiveness in research workflows with human-in-the-loop gates and domain-specific auditors.

Language Models & Multi-Agent Claude Code Research Workflow Human-in-the-Loop

Dynamic Model for Planning Biomechanically Realistic Behaviors

Building planning & generation models with deep state space models.

Embodied Agents & RL Generative Models Computational Neuroscience Deep State Space Model Generative Model

Multimodal Model Embodied Simulation

Reverse engineering from a embodied language model's perspective.

Language Models & Multi-Agent MLLM Probing LLM-ology

Agent-based Multi-collaboration Framework

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

Language Models & Multi-Agent Multi-agent Inference System Adversarial Learning

Learn From Your Enemy

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

Embodied Agents & RL Deep Reinforcement Learning RL Environment Adversarial Learning

Latent Planning as Optimization

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

Embodied Agents & RL Data Efficient Sampling 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.

Representation & Topology Computational Neuroscience Computational Topology

Personalized Database For Study Data

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

Applied Data Science Data Science Workflow Vectorized Database

Recommendation Systems for Business Owners

Building recommendation systems using sequential data for business owners.

Applied Data Science Recommendation Systems Data Science Workflow Deep Learning

Robust Ensemble Learning

Ensemble learning in highly imbalanced real-world datasets.

Applied Data Science Data Science Workflow Machine Learning

Multi-addicted State Q-agent Decision Making

Studying effects of addition computationally via discrete reinforcement learning.

Embodied Agents & RL Computational Neuroscience Reinforcement Learning

Laplacian Eigenmap Visualization

Intuitive visualization of dimensional reduction algorithm for educational purpose.

Representation & Topology Visualization Representation Learning