Paper-Conference

Compressing Large Language Models by Joint Sparsification and Quantization

Outlier Suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling

Lossy and Lossless (L2) Post-training Model Size Compression

Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization

Annealing-Based Label-Transfer Learning for Open World Object Detection

SysNoise: Exploring and Benchmarking Training-Deployment System Inconsistency

Exploiting Subgraph Similarities for Efficient Auto-tuning of Tensor Programs

Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models

QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization

NNLQP: A Multi-Platform Neural Network Latency Query and Prediction System with An Evolving Database