Conference

One collaboration paper on “Swift: Fast Secure Neural Network Inference with Fully Homomorphic Encryption” is accepted by IEEE TIFS'2025.

Four papers on efficient LLM are accepted by DAC'2024 as regular papers.

Four papers, including 3 on efficient AI and 1 on privacy-preserving AI, are accepted by DATE'2025 as regular papers.

Two papers on “PrivCirNet: Efficient Private Inference via Block Circulant Transformation” and “ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction” are accpted by NeurIPs'2024.

One paper on “CASCADE: A Framework for CNN Accelerator Synthesis with Concatenation and Refreshing Dataflow” is accepted by IEEE TCASI'2024.

Dr. Meng Li delivered three talks in CCF Chip 2024 on efficient and private AI.

One paper on “Trinity: A General Purpose FHE Accelerator” is accepted by DATE'2024 as a regular paper. This is a joint work w/ Prof. Mingzhe Zhang from IIE CAS and Ant Group.

Seven papers, including 2 papers on privacy-preserving AI and 5 papers on efficient AI, are accepted by ICCAD'2024 as regular papers.

Three papers on efficient and privacy-preserving deep learning are accepted by DAC'2024 as regular papers, includin “Alchemist: A Unified Accelerator Architecture for Cross-Scheme Fully Homomorphic Encryption”, “FastQuery: Communication-efficient Embedding Table Query for Private LLMs inference”, and “MoteNN: Memory Optimization via Fine-grained Scheduling for Deep Neural Networks on Tiny Devices”.

One paper on “MixCIM: A Hybrid-Cell-Based Computing-in-Memory Macro with Less-Data-Movement and Activation-Memory-Reuse for Depthwise Separable Neural Networks” is accepted by IEEE CICC'2024.