Flexible Inference for Predictive Coding Networks in JAX.

Official implementation of our NeurIPS 2025 poster paper "PID-controlled Langevin Dynamics for Faster Sampling of Generative Models"

A post-connectionist blueprint for persistent, autopoietic AGI. This framework redefines intelligence as dynamical self-stabilization, moving from "AI as a tool" to "AI as a persistent entity" through recursive self-modeling, active inference, and non-equilibrium thermodynamics.

A comprehensive collection of implementations for Deep Generative Models, including VAEs, Normalizing Flows, CycleGAN, EBMs, Score-Based Models, Diffusion (DDPM/DDIM), and Flow Matching. Features applications in Anomaly Detection, Disentanglement, Style Transfer, Subject-Driven Generation (DreamBooth), and Financial Time Series Synthesis.

Multimodal LLM hallucination quantification via KL-smoothed scores + spectral/energy models (RKHS, hypergraphs).

A research-focused modular generative modeling library built on JAX/Flax NNX

Experimental validation workspace for Extropic THRML: thermodynamic computing with JAX-accelerated block Gibbs sampling

Investigating the mathematical links between Statistical Mechanics and AI. Phase 1 features a vectorized 2D Ising Model simulation (Metropolis-Hastings) with real-time thermodynamic analysis to demonstrate how local physical interactions drive emergent intelligence.

A generalized reinforcement learning framework for structured action representations and adaptive decision-making in evolving systems.

RailMind — Dissipative Neural Architecture. Emergent structure through energy competition.

My master's thesis focused on teaching robots from a raw visual input.

🤖 Notes, assignments & projects for CS-844 Generative Deep Models — NUST CEME. Topics: Autoregressive Models, VAEs, GANs, Diffusion, Score-Based Models, LLMs & CLIP. Built with Python · PyTorch.