Skip to content
View HaochengLu's full-sized avatar
6 followers · 0 following

Achievements

Achievement: Pull Sharkx3Achievement: Starstruckx2Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: Starstruckx2Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Quickdraw

Block or report HaochengLu

Report abuse

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

Report abuse
HaochengLu/README.md

Haocheng Lu

I am a computer science student and systems engineer interested in building reliable AI systems.

Focus

  • Agent OS - durable, permission-aware runtimes for long-lived agent workflows.
  • Recursive Self-Improvement (RSI) - data-centric training, benchmark design, and evaluation for agents.
  • Molecular Parsing - scientific document understanding, molecule detection, and structured chemical extraction from PDFs.
  • Context & Runtime Governance - versioned context, pre-action guardrails, and verifiable execution.

Selected Work

Incoming M.S. student in Computer Science at Columbia University; B.S. in Computer Science from NYU Shanghai.

I enjoy turning research ideas into reproducible systems, benchmarks, and open-source tools.

Pinned Loading

  1. evolvent-ai/RSIBench-Data evolvent-ai/RSIBench-Data Public

    Synthetic data generation, post-training, and E2B benchmark evaluation infrastructure.

    Shell 167 8

  2. contextvc contextvc Public

    Git-native context control plane for AI coding agents

    Rust 143 6

  3. GapHarness GapHarness Public

    Certificate-carrying runtime harness compilation for API-only LLM agents.

    Python

  4. career-engine career-engine Public

    AI career strategy engine that analyzes resume evidence with multi-agent review and generates personalized career path recommendations.

    TypeScript 1