Research

In Phase II, TILOS advances a new paradigm of optimization-driven intelligent systems spanning chips and autonomous systems, unifying advances in AI, optimization, and embedded systems.

Our mission: to co-advance the next generation of AI and optimization, driven by the complexities of physically embedded real-world intelligence, while cultivating the workforce needed to shape this area.

TILOS Publications on Google Scholar (opens in a new tab)

Software & Datasets

Research Thrusts

  • Research Thrust 1

    Foundations

    Core principles for optimizing AI models to learn, reason, and generalize more effectively and efficiently, from adaptive post-training to trustworthy intelligence.

    • F1Adaptive Intelligence
    • F2Efficient Intelligence
    • F3Generalizable Intelligence
    • F4Trustworthy Intelligence
    • F5Foundations of Agentic Intelligence
    • F6Generative & Learning-based Optimization

  • Research Thrust 2

    Embodied Multi-Agent AI

    How large populations of embodied agents learn, coordinate, and act under uncertainty, communication constraints, and safety requirements.

    • E1Embodied World Models
    • E2Multi-agent Optimization
    • E3Safety and Trust for Multi-agent Systems

  • Research Thrust 3

    AI Hardware Substrate

    A closed-loop, AI-native hardware–software ecosystem that integrates AI for hardware design with hardware for AI.

    • H1AI-Native Chip Design and EDA
    • H2Adaptive, Multimodal, and Robust AI Accelerators
    • H3AI-Agent-Driven Programming, Compilation, and Runtime
    • H4Security, Reliability, and Traceability