Distributed Newton Fractal Permalink
Published:
Computes Newton–Raphson fractals on Distributive’s web5 compute framework. Worker code is Python compiled to WebAssembly via Bifrost, so the same algorithm runs inside any browser-based DCP worker.
Posts by Collection
projects
DCP Tutorial #6 — Distributed Double Pendulums Permalink
Published:
Tutorial showing how to compute thousands of chaotic double-pendulum simulations in parallel on the Distributive Compute Protocol. Each worker computes one pendulum’s trajectory from a unique initial condition.
ArtificialPersona Permalink
Published:
Real-time anonymous voice and visual communication built on speech-to-text, text-to-speech, and deepfake pipelines. Queen’s University team project.
Multi-Directional Ablation of Refusal in LLMs Permalink
Published:
Tests whether LLM refusal is mediated by multiple directions rather than a single one. Two-direction ablation outperforms the one-direction baseline — but not via the top-two ranked vectors.
Discord LLM Chatbot Permalink
Published:
Discord bot with multi-agent dialogue, vision, and per-channel chat memory. Wraps any OpenAI-compatible API so it can sit in front of self-hosted local LLMs.
LibreChat-Image Permalink
Published:
Personal fork of LibreChat adding standalone image-generation capabilities (NovelAI-style) and extra endpoint support on top of the upstream multi-provider chat UI.
Lumiverse Permalink
Published:
Self-hostable AI chat platform with a sandboxed in-worker extension runtime. Bun + Hono + bun:sqlite (WAL, zero-ORM), Web Crypto for secrets at rest, native WebSocket event bus, and a typed RPC surface that lets third-party extensions reach chats, characters, generation, and macros under per-user scope.
LumiRealm: RisuAI Compatibility Runtime Permalink
Published:
An extension that ports the entire RisuAI character-card runtime (Lua triggers, ~179 CBS macros, lorebook decorators, fixed-position widgets, modules, in-app character browser) onto Lumiverse. Translator pipeline at import time, dispatch + sandboxed Lua at generation time, shadow-DOM-isolated rendering at paint time.
StructMemoryR1 — Tree-Structured Memory with RL Permalink
Published:
Three cooperating GRPO agents that build, query, and reason over a tree-structured memory of long multi-session dialogue. +9.0 F1 multi-hop and +13.8 F1 temporal vs. the strongest non-oracle baseline on LoCoMo.
LumiAgent: In-Chat Tool-Calling Agent Permalink
Published:
A tool-calling LLM agent embedded directly in a frontend chat application, with full read/write access to characters, chats, prompts, personas, presets, and the assembled prompt. Every mutation flows through a diff layer with dependency-aware revert.
LumiBooks: Hierarchical Chat Memory Permalink
Published:
Two-tier in-place summarization for long chat histories. Older messages compress into ‘chapters’, chapters bind into ‘arcs’, summaries splice back where the originals lived so prompt order is preserved and context stays bounded. Stored as editable world-book entries with preview-before-save.
Google Reverse Proxy Permalink
Published:
OpenAI-compatible reverse proxy for Google’s AI products (Gemini CLI, Google AI Studio). Multi-account pool with quota balancing, failover, and a single bearer-token endpoint.
publications
Natural Language PDDL (NL-PDDL) for Open-world Goal-oriented Commonsense Regression Planning in Embodied AI
Published in ICLR 2026 (Poster), 2026
A neurosymbolic agentic planning framework that enforces sound and deterministic reasoning for LLM-based agents in open-world environments, improving previous baselines by 373% and attaining state-of-the-art across central benchmarks.
Recommended citation: Xiaotian Liu, Armin Toroghi, Jiazhou Liang, David Courtis, Ruiwen Li, Ali Pesaranghader, Jaehong Kim, Tanmana Sadhu, Hyejeong Jeon, Scott Sanner. (2026). "Natural Language PDDL (NL-PDDL) for Open-world Goal-oriented Commonsense Regression Planning in Embodied AI." International Conference on Learning Representations (ICLR).
Download Paper
talks
teaching
CISC 101: Introduction to Computer Programming
Teaching Assistant, Queen's University, 2022
Introduction to algorithms: their definition, design, coding, and execution on computers. Intended for students who have no programming experience.
COGS 100: Introduction to Cognitive Science
Teaching Assistant, Queen's University, 2023
A multidisciplinary approach to the study of the mind combining approached from philosophy, psychology, linguistics, neuroscience, anthropology, and artificial intelligence. Logic, rules, concepts, and other mental representations used to generate thought and behaviour. Implementation of computational and cognitive models of mental processes.
CISC 235: Data Structures
Teaching Assistant, Queen's University, 2023
Design and implementation of advanced data structures and related algorithms. Topics will include complexity analysis, trees, graphs, hash tables, queues and heaps, sorting, and shortest paths.
CISC 352: Artificial Intelligence
Teaching Assistant, Queen's University, 2024
An introduction to the basic principles and tools of artificial intelligence. Problem solving methods and knowledge representation techniques. Apply search to game-playing and to solve Constraint Satisfaction Problems and the intelligent agent paradigm as an underlying model for exploring AI problem domains, tools, and techniques.
MIE 223: Data Science
Teaching Assistant, University of Toronto, 2026
Introduction to the methods of Data Science. Exploratory data analysis and visualization; tools for reproducible analysis. Principles and tools for data collection; awareness of bias in collection methods. Data cleaning. Descriptive statistics and feature analysis. Assessment of data with respect to scientific theories. Data interpretation fallacies. Geographical data representation and manipulation. Text processing, the natural language processing pipeline, and sentiment analysis. Fundamentals of social network analysis and centrality measures. Cloud-based data processing.