STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization
"模型精度" 相关文章
Optimized Layerwise Approximation for Efficient Private Inference on Fully Homomorphic Encryption
Evaluation of Differential Privacy Mechanisms on Federated Learning
Evaluation of Differential Privacy Mechanisms on Federated Learning
On the Implicit Adversariality of Catastrophic Forgetting in Deep Continual Learning
Logistic-Gated Operators Enable Auditable Unit-Aware Thresholds in Symbolic Regression
Quantization Range Estimation for Convolutional Neural Networks
Quantization Range Estimation for Convolutional Neural Networks
Quantization Range Estimation for Convolutional Neural Networks
FedEL: Federated Elastic Learning for Heterogeneous Devices
DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
Intelligent Sampling of Extreme-Scale Turbulence Datasets for Accurate and Efficient Spatiotemporal Model Training
Caching Techniques for Reducing the Communication Cost of Federated Learning in IoT Environments
关于 DeepSeek-R1 API 评测，至少有 7 个误区
老显卡福音！美团开源首发INT8无损满血版DeepSeek R1
GPU推理时代终结？世界最大芯片加持推理狂飙20倍，英伟达H100也被干趴
