News

Paper “CryptoMoE:Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing” and “EfficientNav:Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval” are accepted to NeurIPS2025 (acceptance rate:26%)!

Collaboration Paper “Ironman:Accelerating Oblivious Transfer Extension for Privacy-Preserving AI with Near-Memory Processing” is accepted by MICRO'25 (CCF A)!

Paper “Breaking the Layer Barrier:Remodeling Private Transformer Inference with Hybrid CKKS and MPC” is accepted by USENIX Security 2025 (acceptance rate:17%)!

Collaboration Paper “Swift:Fast Secure Neural Network Inference with Fully Homomorphic Encryption” is accepted by IEEE Transactions on Information Forensics & Security (TIFS)!

I received a complimentary professional membership of Association for Computing Machinery (ACM)!

Paper “PrivCirNet:Efficient Private Inference via Block Circulant Transformation” is accepted to NeurIPS2024 (acceptance rate:26%)!

Paper “PrivQuant:Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization” and “FlexHE:A flexible Kernel Generation Framework for Homomorphic Encryption-Based Private Inference” are accepted to ICCAD2024 (acceptance rate:23%)!

Paper “FastQuery:Communication-efficient Embedding Table Query for Private LLM Inference” is accepted by DAC2024 (acceptance rate:26%)!

Paper “Falcon:Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inference” is accepted by ICCAD 2023 (acceptance rate:23%)!