Dynamic Low-Rank Sparse Adaptation for Large Language Models.
CoRR, February, 2025
KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference.
CoRR, February, 2025
RazorAttention: Efficient KV Cache Compression Through Retrieval Heads.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
RazorAttention: Efficient KV Cache Compression Through Retrieval Heads.
CoRR, 2024
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Quantized Winograd Acceleration for CONV1D Equipped ASR Models on Mobile Devices.
Proceedings of the IEEE International Conference on Acoustics, 2022
Extremely Low Footprint End-to-End ASR System for Smart Device.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021
INT8 Winograd Acceleration for Conv1D Equipped ASR Models Deployed on Mobile Devices.
,
,
,
,
,
,
,
,
,
,
CoRR, 2020
Effective Pipeline for Compressing Deep Object Detectors.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020
Fully Parallel Architecture for Semi-global Stereo Matching with Refined Rank Method.
CoRR, 2019
Creating Lightweight Object Detectors with Model Compression for Deployment on Edge Devices.
CoRR, 2019
Efficient Implementation of Convolutional Neural Networks with End to End Integer-Only Dataflow.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2019
High effective medical image segmentation with model adjustable method.
Proceedings of the 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013), 2013
The decimator with multiplier-free realizations for high precision ADC applications.
Proceedings of the IEEE 10th International Conference on ASIC, 2013
A low power IC for efficient de-interlacing based on refined motion adaptive method.
Proceedings of the 21st IEEE International Symposium on Industrial Electronics, 2012
An information integration system of signal intersection with multi-mode traffic data collection and analysis.
Proceedings of the 21st IEEE International Symposium on Industrial Electronics, 2012