Skip to content
View Justin0504's full-sized avatar
🎯
Focusing
🎯
Focusing
58 followers · 2 following

Achievements

Achievement: Starstruckx3Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Starstruckx3Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Block or report Justin0504

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. Markdown is supported. 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
Justin0504/README.md

Hi, I'm Aojie (Justin) Yuan · 袁傲杰

I build powerful, human-centered LLMs — reliable enough to trust with real-world resources. M.S. in Computer Engineering (Honors) at USC, researching at FORTIS Lab with Yue Zhao · Shanghai Jiao Tong University alumnus.

Research: agent safety · LLM reasoning & interpretability · world models

🌐 aojieyuan.com · 中文主页 · 🎓 Google Scholar · 📝 Writing · ✉️ aojieyua@usc.edu

Building

Selected papers (2026)

→ All 15 papers, each with a plain-language explainer: aojieyuan.com

Pinned Loading

  1. Aegis Aegis Public

    Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.

    TypeScript 522 47

  2. Sovereign-OS Sovereign-OS Public

    Constitution-first AI orchestration: one Charter (YAML) defines mission, budget & rules. CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP. Think…

    Python 93 13

  3. BrewNet BrewNet Public

    Swift 10 5

  4. Verifiable_agent Verifiable_agent Public

    SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution FAGEN @ICML , AI4GOOD @ICML

    Python 4

  5. thought-kv-hierarchy thought-kv-hierarchy Public

    Semantics-aware memory hierarchy for KV-cache in LLM reasoning. Offloads low-importance reasoning tokens from HBM to DDR instead of evicting them, preserving accuracy at reduced memory cost.

    Python 4

  6. parallel-hybrid-retrieval parallel-hybrid-retrieval Public

    Parallelizing a hybrid sparse-dense retrieval pipeline for long-term AI agent memory with OpenMP. Features BM25 + HNSW fusion, SIMD/MaxScore optimizations, temporal partitioning (47x speedup), and …

    C++ 4 1