Skip to content
View HowieHwong's full-sized avatar

Highlights

  • Pro

Block or report HowieHwong

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
HowieHwong/README.md
Yue Huang 黄跃 — building human-centered, self-evolving AI systems

Website  ·  Scholar  ·  X  ·  LinkedIn  ·  Email  ·  CV

Past · Present

University of Notre Dame    Microsoft Research    MIT-IBM Watson AI Lab    Cornell University    Tsinghua University    Sichuan University

Hi there 👋

I am a third-year PhD student at the University of Notre Dame, advised by Prof. Xiangliang Zhang in the MINE Lab.

Previously at Microsoft Research, MIT-IBM Watson AI Lab, IBM Research, and Tsinghua KEG.

Research

I build self-improvement humane and humanized intelligence: foundation models and agentic systems aligned with human values, informed by human cognition, and supported by reliable infrastructure.

Alignment

I study how to align foundation models and agentic systems with human values, from individual behavior to collective dynamics. My work uncovers emergent social intelligence risks that agent-level safeguards alone cannot prevent (Emergent Social Intelligence Risks Nature Machine Intelligence). I also benchmark trustworthiness (TrustLLM ICML'24, TrustGen ICLR'26), train honest and helpful models (HonestLLM NeurIPS'24), examine biases in LLM-as-a-judge (Justice or Prejudice? ICLR'25), and prioritize safety in alignment (SPA AAAI'26 Oral, Capability-Oriented Risk ICML'26).

Cognition

I probe how models reason and perceive, deciding when to use tools (MetaTool ICLR'24), adapting reasoning style to the task (AdaReasoner NeurIPS'25 Spotlight), exposing flaws in social character simulation (TrustSim COLM'25), diagnosing failure modes at scale (ProbeLLM ICML'26), ranking models by question difficulty (RankLLM ICLR'26), and probing visual aesthetic judgment (VAB COLM'26). I also explore emotionally-adaptive generative AI (EmoNest NeurIPS'25 Creative, NARRA-Gym NeurIPS'26, Omelune Mac app).

Infrastructure

I build the toolchain that makes the above possible: frameworks for unified synthetic data (DataGen ICLR'25, ChemOrch NeurIPS'25), synthetic interaction data for scalable personalization (PersonaGym KDD'26), foundational guardrails for safer agentic systems (Safiron ICLR'26), a new guardian model paradigm (Guardian-as-an-Advisor ACL'26 Findings), agent infrastructure that turns compute into verifiable improvement and has broken 120 world records in mathematics (Épi Bake AI), and infrastructure for recursive self-improvement (RSI Arena Live at COLM'26).

Recent contributions

google-deepmind/formal-conjectures teorth/optimizationproblems Erich's Packing Center: Pentagons in Triangles: n = 30, 36, 39

3D contribution calendar

Pinned Loading

  1. TrustLLM TrustLLM Public

    [ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs and AI agent orchest…

    Python 636 70

  2. TrustGen/TrustEval-toolkit TrustGen/TrustEval-toolkit Public

    [ICLR'26, NAACL'25 Demo] Toolkit & Benchmark for evaluating the trustworthiness of generative foundation models.

    Python 136 11

  3. MemoHarness MemoHarness Public

    MemoHarness: Agent Harnesses That Learn from Experience

    Python 114 19

  4. ydyjya/Awesome-LLM-Safety ydyjya/Awesome-LLM-Safety Public

    A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights i…

    HTML 1.9k 122

  5. MetaTool MetaTool Public

    [ICLR'24] MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use

    Python 121 12

  6. DataGen DataGen Public

    [ICLR'25] DataGen: Unified Synthetic Dataset Generation via Large Language Models

    Python 69 4