Production-deployed platform combining AI and quantum-randomness for identity signatures.

A simulator using multi-agent LLMs to reproduce hateful content cascades for moderation research.

A verifiable benchmark for small-molecule preclinical pharmacology AI agent evaluation.

A large-scale open-source RTS game used as a testbed for strategic reasoning in AI agents.

A reinforcement learning environment for RoboCup 2D Soccer Simulation.

A clinical ASR benchmark designed to evaluate robustness to multiscript variability.

A graph database built for LLM agents, described as 'Supabase for graphs'.

A fusion architecture for multi-vector fraud and AML detection in retail and corporate banking.

Algorithm for dynamic LLM selection under resource budgets and service-level requirements.

Residual on Embedded Features Gaussian Process for geometry-aware uncertainty quantification.

Applying GraphSAGE networks for intrusion detection and drone swarm coordination

Paper analyzing LLM inference efficiency across different AI accelerator platforms.

Open-source browser-based app for interactive exploration of quantum hardware.

A Transformer-based model using fixed-point convergence for adaptive compute in looped architectures.

A method for decoupling and editing modality-specific neurons in Multimodal Large Language Models.

Query-adaptive agent framework for wearable health question answering.

A method for quality-aware self-distillation for GUI grounding in VLMs.

A study on pricing flash endurance for embodied agents to optimize device lifetime.

A unified framework for learning vessel trajectory embeddings based on the MoCo paradigm.

Code for an AlphaZero-based agent for the strategic board game WallGo.