Skip to content

My Projects

Selected work in AI research, systems, and creative applications.

Prompt Warrior

An experimental roguelike game built in Godot with deep integration of large language models. Player actions, world state and game rules are interpreted and resolved in real time using diffusion-based text models. Every stage is defined completely in natural language, resulting in a fluid and creative experience for players and builders.

ELODIN: Naming Concepts in Embedding Spaces

During my time as a Computer Vision Research Scientist at Modelme, I worked on generating photorealistic virtual fashion photoshoots using diffusion models. I developed a novel method using custom CLIP-based embeddings to achieve better consistency in pose and angle across generated images of the same virtual model. I was involved from the initial research and ideation through to production deployment of the image generation pipeline. This work resulted in the research paper "ELODIN: Naming Concepts in Embedding Spaces" (arXiv:2303.04001).

Hytale Code Explainer

RAG over a decompiled codebase: Qdrant vector database, mxbai-embed-large embeddings, dense retrieval with keyword boosting, RAGAS evaluation, LiteLLM proxy for multi-provider LLMs, and a Docker Compose setup. Served through a Discord bot so modding teams can find the exact files they need.

Latent Translation

A technical project exploring the translation of latent representations between different generative models. An MLP was trained to map latents from EffNet (Stable Cascade) into CLIP’s latent space, enabling semantic comparisons without processing images through the pixel domain.

AI Rooms

A text-based escape room game where players interact with the environment using freeform natural language. Each object in the room functioned as its own autonomous agent. The system used structured generation to maintain consistency across agent behaviors and game state while allowing creative player input.