Mu Yuan (袁牧)

secure-transformer-inference. [NDSS 2026] Secure Transformer Inference is a protocol for serving Transformer-based models securely.

InFi. [MobiCom 2022] InFi is a library for building input filters for resource-efficient inference.

PacketGame. [SIGCOMM 2023] PacketGame: Multi-Stream Packet Gating for Concurrent Video Inference at Scale

scx. [SIGCOMM 2025] SCX: Stateless KV-Cache Encoding for Cloud-Scale Confidential Transformer Serving

MLink. Repository for AAAI'22 paper "MLink: Linking Black-Box Models for Collaborative Multi-Model Inference".

citation-impact. Citation Impact Analyzer helps researchers understand how their papers are cited.

tech-in-papers. Techniques in papers, personal learning logs

ForesightLM. Prediction-in-the-Loop agent paradigm implementation.

html-slides-to-pdf. Convert your HTML slides to PDF (for better sharing).

nvselector. Auto Selector for NVIDIA GPUs

PrivacyModelZoo. The ModelZoo for Hi-Privacy project.