Patents and projects spanning reinforcement learning, ML tooling, rendering, game engines, and research platforms.
Patents
Agentically-Orchestrated Foundational Models for Cloud Architecture Development
US20250343728 · Application ID 18651871
User response information is obtained, comprising information indicative of cloud architecture requirements for a cloud architecture to fulfil.
A plurality of agentic orchestration models - each a machine-learned language model prompted to fulfil a corresponding cloud-architecting role - generate role outputs, one of which proposes generic component placeholders for components necessary to meet the requirements.
Based on the role outputs, a proposed architecture output is generated, comprising a visual representation of the proposed generic component placeholders.
An invite-only research workspace for academics: a library that builds itself by automatically extracting papers, side-by-side PDF and note viewing, AI assistants for summarising and drafting, citation-graph visualisation, and customisable workspaces that adapt to how researchers actually work.
An exploration of game-engine architecture: cross-platform Vulkan, WebGL, ImGui, JoltPhysics (used in Horizon Forbidden West), SoLoud, ECS, and C++ scripting, with particular attention to creating APIs for ML training.
An adaptation of BloodHound from cybersecurity, brought to model architectures and policies - extracting insights across checkpoints into the state of the gradients with architecture-aware visuals.
A C++ parser for math expressions that looks up each glyph's outline in a loaded OpenType font (TTF / OTF) and emits an extruded triangle mesh ready for any renderer. No graphics-API dependency: the library returns flat vertex/index buffers for custom rendering.
Diversified model architectures and training algorithms in a modular, extensible framework for running RL training experiments. The goal: consistent metrics, visualisations, compatibility with GradientHound for debugging, and quick research iteration. Currently private and in active development.
RLResearch
Vanilla MuJoCo - JoltGym
Exploring educationally whether using Jolt for multi-agent training can be as (or more) efficient than MuJoCo - recreating the physics of environments like Humanoid / HalfCheetah, making Gym wrappers, and training RL.
Leveraging TorchLib and custom integration layers with ImGui and Wandb to enable re-use of RL methods in other C++ projects - particularly to build and train agents that can act in 3D environments alongside human-controlled agents.
