Tianshi Xu | 李萌的个人主页https://mengli.me/zh/authors/tianshi_xu_2023g/Tianshi XuWowchemy (https://wowchemy.com)zh-Hanshttps://mengli.me/media/icon_hu_ad1e0b0e8ea3c209.pngTianshi Xuhttps://mengli.me/zh/authors/tianshi_xu_2023g/Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPChttps://mengli.me/zh/publication/usenix-2025-blb/Wed, 14 May 2025 00:00:00 +0000https://mengli.me/zh/publication/usenix-2025-blb/PrivCirNet: Efficient Private Inference via Block Circulant Transformationhttps://mengli.me/zh/publication/neurips-2024-privcirnet/Sat, 14 Dec 2024 00:00:00 +0000https://mengli.me/zh/publication/neurips-2024-privcirnet/FlexHE: A flexible Kernel Generation Framework for Homomorphic Encryption-Based Private Inferencehttps://mengli.me/zh/publication/iccad-2024-flexhe/Sun, 27 Oct 2024 00:00:00 +0000https://mengli.me/zh/publication/iccad-2024-flexhe/PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimizationhttps://mengli.me/zh/publication/iccad-2024-privquant/Sun, 27 Oct 2024 00:00:00 +0000https://mengli.me/zh/publication/iccad-2024-privquant/FastQuery: Communication-efficient Embedding Table Query for Private LLMs inferencehttps://mengli.me/zh/publication/dac-2024-fastquery/Sun, 07 Jul 2024 00:00:00 +0000https://mengli.me/zh/publication/dac-2024-fastquery/Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inferencehttps://mengli.me/zh/publication/iccad-2023-falcon/Tue, 24 Oct 2023 00:00:00 +0000https://mengli.me/zh/publication/iccad-2023-falcon/Swift: Fast Secure Neural Network Inference with Fully Homomorphic Encryptionhttps://mengli.me/zh/publication/tifs-2025-swift/Mon, 01 Jan 0001 00:00:00 +0000https://mengli.me/zh/publication/tifs-2025-swift/