Publications

(2024). PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization. ICCAD 2024.

Paper Link

(2024). FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference. DAC 2024.

PDF Paper Link

(2024). PrivCirNet: Efficient Private Inference via Block Circulant Transformation. NeurIPS 2024.

PDF Code Paper Link