Past research & project that I have worked and am currently working on.
Creating artificial motor cortex by imitating naturalistic agents and performing generative inverse kinematics.
Manifold learning through discrete Morse theory: extracting the topological skeleton of behavioral data instead of flat embeddings.
Details coming later.
Designing hiearchical tokenization scheme, allowing sequence transformers to model and genearte complex molecules better.
A constraint framework enhancing Claude's effectiveness in research workflows with human-in-the-loop gates and domain-specific auditors.
A full-stack web app for tracking study and work time with real-time timers, analytics dashboards, and AI-powered chat.
Farmework for tackling language model multi-agents collborations in an adversarial environment.
Full end-to-end A-MARL framework for competitive and cooperative AI training.
Spectral analysis of calcium imaging reveals a theta-enriched neuron subpopulation that encodes social behavior in mouse prefrontal cortex.
Reverse engineering from a embodied language model's perspective.
Learning is about how to create structured projection space and plan with it during post-training inference.
Leveraging the power of neural network & topological data analysis to study the effect of stress & ruminations.
Building recommendation systems using sequential data for business owners.
Ensemble learning in highly imbalanced real-world datasets.
Studying effects of addition computationally via discrete reinforcement learning.
Intuitive visualization of dimensional reduction algorithm for educational purpose.