Welcome to my GitHub. This repository is a central hub for my research and projects in machine learning, generative flow networks, and computer science.
I'm a researcher focused on Generative Flow Networks (GFlowNets) and their applications to combinatorial optimization, causal inference, and structured decision-making. My work sits at the intersection of probabilistic modeling, deep learning, and algorithm design.
My current interests include:
- Generative Flow Networks and their theoretical foundations
- Causal inference and dynamic equilibrium models
- Combinatorial optimization with learned samplers
- Diffusion models and generative modeling
| Project | Description |
|---|---|
LUCIDE |
Latent Unified Causal Inference through Dynamic Equilibrium — a GFlowNet-based framework for causal structure learning and Bayesian belief revision. |
GFlowNet-Bilevel-Knapsack |
GFlowNet with critic for partition function estimation, applied to bilevel knapsack problems with Benders decomposition. |
GFlowNet-Knapsack-CDF |
A GFlowNet that learns probabilistic solutions to the 0-1 Knapsack problem, enabling efficient global optimization via learned CDFs. |
Diffusion-l1 |
Exploration of diffusion models — implementation and experiments with denoising-based generative processes. |
All content in this repository is shared under the MIT License, unless otherwise specified.