https://github.com/yikaiw/snn
공식 코드Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks
Papers with Code 아카이브
Quantization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 10
- 보존된 평가 기록
- 32
Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).
Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/yisunlp/ott
공식 코드https://github.com/yixuanseanzhou/quantized_neural_nets
공식 코드Post-training Quantization for Neural Networks with Provable Guarantees
https://github.com/yiyuec/fed-qssl
공식 코드Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity
https://github.com/yizhilll/mert
공식 코드MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
https://github.com/yjwu17/ADMM-Compression-for-SNNs
공식 코드Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization
https://github.com/ylsung/rsq
공식 코드RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
https://github.com/ym-shan/orrc-syna-natural-pruning
공식 코드SynA-ResNet: Spike-driven ResNet Achieved through OR Residual Connection
https://github.com/ymoslem/model-compression
공식 코드Efficient Speech Translation through Model Compression and Knowledge Distillation
https://github.com/ynahshan/nn-quantization-pytorch/tree/master/lapq
공식 코드https://github.com/yochaiz/Slimmable
공식 코드Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks
https://github.com/yochaiz/darts-UNIQ
공식 코드Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks
https://github.com/younghyun197/ptq4vm
공식 코드https://github.com/youngkyunJang/GPQ
공식 코드Generalized Product Quantization Network for Semi-supervised Image Retrieval
https://github.com/youngkyunjang/deep-hash-distillation
공식 코드https://github.com/youngkyunjang/spq
공식 코드Self-supervised Product Quantization for Deep Unsupervised Image Retrieval
https://github.com/youngseng/qpgesture
공식 코드https://github.com/youngsheen/SimVQ
공식 코드Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
https://github.com/ytgui/spt-proto
공식 코드SPT: Fine-Tuning Transformer-based Language Models Efficiently with Sparsification
https://github.com/yu-zhewen/mixed-td
공식 코드Mixed-TD: Efficient Neural Network Accelerator with Layer-Specific Tensor Decomposition
https://github.com/yuanli2333/Hadamard-Matrix-for-hashing
공식 코드Central Similarity Quantization for Efficient Image and Video Retrieval
https://github.com/yuhuixu1993/SLQ
공식 코드Deep Neural Network Compression with Single and Multiple Level Quantization
https://github.com/yuhuixu1993/Trained-Rank-Pruning
공식 코드https://github.com/yuliangyan0807/llm-fingerprint
공식 코드DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection
https://github.com/yulongtzzz/Stealthy-Backdoors-as-Compression-Artifacts
공식 코드https://github.com/yun224/dukd
공식 코드Data Upcycling Knowledge Distillation for Image Super-Resolution
https://github.com/yunshiwen/vqshape
공식 코드https://github.com/yxli2123/loftq
공식 코드LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models
https://github.com/yzhao062/pytod
공식 코드TOD: GPU-accelerated Outlier Detection via Tensor Operations
https://github.com/z-hXu/ReCU
공식 코드https://github.com/z1zyw/vq-map
공식 코드VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
https://github.com/zackschen/cucl
공식 코드https://github.com/zavareh1/ClippedQuantFL
공식 코드Communication-Efficient Federated Learning via Clipped Uniform Quantization
https://github.com/zaydzuhri/softpick-attention
공식 코드Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
https://github.com/zbr17/OptVQ
공식 코드Preventing Local Pitfalls in Vector Quantization via Optimal Transport
https://github.com/zetyquickly/DensePoseFnL
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.