About
Incoming DPhil student in computer science, starting autumn 2026. Currently ML Research Engineer at CoSTAR National Lab working on video and world models for virtual production. Previously research intern at UIUC Blender Lab (energy-based models). MSc AI (Distinction) from the University of Essex, supervised by Prof. Luca Citi.
Research Interests
I work on generative models for inverse problems. Measurements are usually partial and noisy, so the interesting part is the prior. I use diffusion and score-based models, flow matching and stochastic interpolants, Schrödinger bridges, optimal transport, and energy-based models as learned priors and samplers, built on ODEs and SDEs, Fokker-Planck, and Itô calculus.
I find general methods particularly interesting which improve with data, compute, and better algorithms that don't compete with learning from data. Amortised and simulation-based inference is that bet in practice. Pretrain once, then answer each new case from knowledge with calibrated uncertainty.
Current focus. A common view of diffusion, Schrödinger bridges, flows, and energy-based models through statistical mechanics and differential geometry, with cardiac digital twins as the testbed.
Writing
New Video World Models, on turning slow bidirectional diffusion into real-time interactive simulators. Causality, self-forcing, attention sinks.
News
- New Joined CoSTAR National Lab as ML Research Engineer - Feb. 2026
- Research Collaboration with UIUC Blender Lab - Jul. 2025
- MSc defended at Essex (NIR thesis) - Oct. 2024
Awards
- Full scholarship for MSc AI, University of Essex
Education
University of Essex
MSc Artificial Intelligence (Distinction)
2023 - 2024
Dissertation: NIR — Neural Integration of Iterative Reasoning in LLMs for Code Generation
🥇 1st place, Inter-Departmental Neural Network Challenge (100+ participants)
University of Kurdistan
BEng Computer Engineering
2014 - 2018
Thesis: EfficientCoF — Subspace clustering for collaborative filtering
Experience
CoSTAR National Lab
ML Research Engineer
Feb 2026 - Present
Generative video and world models for virtual production. [Profile]
UIUC Blender Lab
Research Intern
Jul 2025 - Jan 2026
Energy-based transformers for image/video generation. Investigating mode collapse, inference-time compute scaling, and fast sampling strategies.
University of Essex
Postgraduate Researcher
Apr 2024 - Oct 2024
Developed NIR framework for integrating iterative reasoning into LLM hidden states without fine-tuning.
Open Source
Developer & Maintainer
2019 - Present
TorchEBM, cuRBLAS, TransformerX, Emgraph, Bigraph, TASE. See Projects section.
Projects
TorchEBM 🍓
Updated Read more
PyTorch library for energy-based models, diffusion, and flow matching. Implements samplers, score/flow/contrastive objectives, SDE/ODE integrators, interpolants, and mixed-precision training.
PyTorch · CUDA
WorldKernels 
Soon High-throughput world model inference engine. Stateful session management for BiD and AR world models (DreamDojo, Cosmos, DreamZero, etc.) with persistent KV-cache, CUDA graph capture, continuous batching, speculative decoding, and torch.compile fusion. Sub-millisecond scheduling via async token queues; REST/WebSocket streaming with backpressure.
PyTorch · CUDA · Python
cuRBLAS 🍒
GPU-accelerated randomized linear algebra. CUDA kernels for Hutchinson trace estimation, randomized SVD, and probabilistic matrix operations—useful for sliced score matching and large-scale ML.
C++ · CUDA · Python
TransformerX
Modular transformer research library. Composable attention mechanisms, positional encodings, and architecture variants for rapid prototyping.
TensorFlow
Emgraph
Knowledge graph embedding library. Train and evaluate TransE, DistMult, ComplEx, and other relational models on link prediction tasks.
TensorFlow 2
Bigraph
Bipartite graph link prediction. Implements Jaccard, Adamic-Adar, Common Neighbors, Preferential Attachment, and Katz similarity for two-mode networks.
NetworkX · NumPy
Large-scale audio search engine. Scalable indexing and retrieval with Elasticsearch, ArangoDB, and Redis for real-time multimodal search.
Elasticsearch · Python
