Halfrost-Field
《HTTP/2 Protocol Analysis》This series article detailed analysis the RFC 7540, which is the Hypertext Transfer Protocol Version 2 (HTTP/2).
• [RFC 7540] Hypertext Transfer Protocol Version 2 (HTTP/2) • Unveiling the veil of HTTP/2: How does HTTP/2 establish a connection? • Multiplexing of HTTP frames and streams in HTTP/2 • Frame definition in HTTP/2 • HTTP semantics in HTTP/2 • Considerations in HTTP/2 • Frequently asked questions in HTTP/2 • [RFC 7541] HPACK: Header Compression for HTTP/2 • Detailed HTTP/2 header compression algorithm-HPACK • HTTP/2 HPACK practical application examples • [RFC 7301] TLS Application-Layer Protocol Negotiation Extension
《TLS 1.3 Protocol Analysis》This series article detailed analysis the RFC 8846, which is the Transport Layer Security (TLS) Protocol Version 1.3.
• How to deploy TLS 1.3 ？ • [RFC 6520] TLS & DTLS Heartbeat Extension • [RFC 8446] The Transport Layer Security (TLS) Protocol Version 1.3 • TLS 1.3 Introduction • TLS 1.3 Handshake Protocol • TLS 1.3 Record Protocol • TLS 1.3 Alert Protocol • TLS 1.3 Cryptographic Computations • TLS 1.3 0-RTT and Anti-Replay • TLS 1.3 Compliance Requirements • TLS 1.3 Implementation Notes • TLS 1.3 Backward Compatibility • TLS 1.3 Overview of Security Properties
《Study Notes of Machine Learning》This study notes is the machine learning course in the coursera, which it’s instructor is Andrew Ng in the Stanford University.
• Week1 —— What is Machine Learning • Week1 —— Linear Regression with One Variable (Gradient Descent) • Week2 —— Multivariate Linear Regression • Week2 —— Computing Parameters Analytically • Week2 —— Octave Matlab Tutorial • Week3 —— Logistic Regression • Week3 —— Regularization • Week4 —— Neural Networks Representation • Week5 —— Neural Networks Learning • Week5 —— Backpropagation in Practice • Week6 —— Advice for Applying Machine Learning • Week6 —— Machine Learning System Design • Week7 —— Support Vector Machines • Week8 —— Unsupervised Learning • Week8 —— Dimensionality Reduction • Week9 —— Anomaly Detection • Week9 —— Recommender Systems • Week10 —— Large Scale Machine Learning • Week11 —— Application Example: Photo OCR
I am a research-oriented machine learning systems engineer working on foundation model infrastructure, alignment, and evaluation. My work focuses on building efficient, reliable systems for large language models while studying the algorithms and data choices that make these models more useful, controllable, and cost-effective in real applications.
At TikTok, my recent work centers on Model-as-a-Service platforms and high-performance LLM inference. I develop serving infrastructure with vLLM and SGLang across model runtime integration, scheduling and continuous batching, KV-cache and memory management, distributed execution, observability, and reliability. This systems work is closely connected to my research on distributed disaggregated inference, preference optimization, instruction-tuning data selection, multimodal evaluation, and retrieval-augmented biomedical summarization.
My broader research spans reinforcement learning for robotics, healthcare sequence modeling, privacy-preserving machine learning, and motion planning. I am especially interested in model-system co-design: how model architecture, inference algorithms, data curation, hardware utilization, scheduling, and distributed runtimes interact. My goal is to advance frontier AI systems that are faster to experiment with, more rigorous to evaluate, and dependable enough to serve at scale.