1. MS, Computer Science计算机科学硕士 · Northeastern University美国东北大学

    Always learning. Focused on neural networks and LLM agents.一直在学。专注于神经网络和 LLM Agent。

  2. B.Econ, Finance金融学 经济学学士 · Minzu University of China中央民族大学

    Pivoted into computer science, and it opened up a new world for me. Finance shapes how I work; CS shapes how I think.转向计算机科学,为我打开了一个新世界。金融塑造了我做事的方式,计算机塑造了我思考的方式。

Projects项目

[ injection 63% → 0% ]

A LangGraph agent answering SEC-filing questions via PageIndex agentic retrieval at $0.0127 per question, served over MCP on Google Cloud Run. A Progent guardrail cut prompt-injection attack success from 63% to 0% over 108 AgentDojo-template attacks and blocked no legitimate email.一个 LangGraph Agent,用 PageIndex agentic 检索回答 SEC 财报问题,每题成本 $0.0127,通过 MCP 提供服务并部署在 Google Cloud Run。Progent 护栏在 108 次 AgentDojo 模板攻击上把 prompt injection 攻击成功率从 63% 降到 0%,且没有拦下任何一封正常邮件。

Live demo ↗在线演示 ↗
PythonLangGraphMCPDockerCloud RunGitHub Actions
[ Bedrock RAG · 2-region AWS ]

CanPlan — RAG Task Planner

AIAIBackend后端

A RAG backend on AWS that turns a daily-living goal into grounded, step-by-step plans, each citing its source. Three measured eval rounds on CanPlan's step-generation service ended at 100% valid citations and a reading level cut from grade 7.2 to 6.0 — and showed the safety guardrail still over-flags (96% → 89% of plans).AWS 上的 RAG 后端,把一个日常生活目标变成有依据、分步骤、每一步都注明出处的计划。对 CanPlan 的步骤生成服务做了三轮实测评估,最终引用有效率 100%,阅读难度从 7.2 年级降到 6.0——同时也表明安全护栏仍然会过度标记(96% → 89% 的计划)。

TypeScriptAWS CDKBedrockS3 VectorsDynamoDBRAG Eval
[ 0.185 MB · F1 0.942 ]

VAD Model Compression

Machine Learning机器学习

Benchmarked PTQ, QAT and distillation on a CRDNN speech-detection model. The sweet spot is 0.185 MB (−57%) at 1.4 F1 points below the FP32 baseline; the smallest model, 0.053 MB, costs 2.6 points. Dynamic quantization was a no-op: only 1.2% of the weights are nn.Linear.在一个 CRDNN 语音检测模型上对比了 PTQ、QAT 和知识蒸馏。最佳平衡点是 0.185 MB(−57%),F1 比 FP32 基线低 1.4 个点;最小的模型 0.053 MB,代价是 2.6 个点。动态量化几乎不起作用:只有 1.2% 的权重是 nn.Linear。

PyTorchSpeechBrainModel Compression
All projects →全部项目 →