2D Generative Models — DDPM, DDIM, GAN, MeanFlow

Four generative model families implemented from scratch and compared under optimal-transport metrics, isolating the trade-off between sample quality and the number of network evaluations needed to draw a sample.

PyTorchDiffusionDDPM / DDIMGANMeanFlowOptimal Transport

SMART-D — LLM-Guided Multi-Agent Reinforcement Learning

A cooperative multi-agent framework that uses a frozen LLM as a training-time macro-planner, then distils the guidance into the policy so the LLM can be removed entirely at deployment.

Multi-Agent RLPPOLLM PlanningSelf-DistillationOvercooked-AIvLLMReinforcement LearningPyTorchLLM

Scene-Specialized DQN for Multi-Level Generalization

A mixture-of-experts agent for the LevDoom Seek and Slay benchmark — five level-specialised DQN experts routed by a learned scene classifier, compressed to fit a deployment size budget.

Deep RLRainbow DQNMixture of ExpertsRNDViZDoomModel CompressionReinforcement LearningPyTorch

Self-Supervised Medical Image Segmentation

Binary segmentation of grayscale medical images, built to isolate one question: does the improvement come from the architecture, or from the initialisation?

Self-Supervised LearningSimCLRTransUNetU-NetPyTorchContrastive Learning

Go Rank Prediction

Predicting a Go player's rank from 1D to 9D out of game records at 80.65% accuracy — treating rank as an ordered quantity rather than nine unrelated classes, with predictions pooled across views, seeds and games.

Ordinal RegressionCORALTransformerBiLSTMCatBoostEnsemblePyTorch