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/kalyan-nakka/on_device_slms_defense
공식 코드https://github.com/kamwoh/orthohash
공식 코드One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
https://github.com/kartikgupta-at-anu/attack-bnn
공식 코드Improved Gradient based Adversarial Attacks for Quantized Networks
https://github.com/kartikgupta-at-anu/md-bnn
공식 코드https://github.com/kaydotdev/stochastic-quantization
공식 코드Robust Clustering on High-Dimensional Data with Stochastic Quantization
https://github.com/kazuhisafujita/kernelgng
공식 코드Characteristics of networks generated by kernel growing neural gas
https://github.com/kazuhisafujita/removebirthupdating
공식 코드https://github.com/kbountro/pSAX
공식 코드https://github.com/kbunte/lvq_toolbox
공식 코드https://github.com/kclip/icl-equalization
공식 코드In-Context Learning for MIMO Equalization Using Transformer-Based Sequence Models
https://github.com/kclip/r_autoeval_plus
공식 코드Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees
https://github.com/kenny-co/sgd-uap-torch
공식 코드Robustness and Transferability of Universal Attacks on Compressed Models
https://github.com/kerautret/GTVimageVect
공식 코드Geometric Total Variation for Image Vectorization, Zooming and Pixel Art Depixelizing
https://github.com/keums/icassp2022-vocal-transcription
공식 코드https://github.com/khawar512/cvpr
공식 코드Image Compression with Recurrent Neural Network and Generalized Divisive Normalization
https://github.com/khoadoan/adversarial-hashing
공식 코드Image Hashing by Minimizing Discrete Component-wise Wasserstein Distance
https://github.com/kiabuzz/treelut
공식 코드https://github.com/kingdalfgoodman/lota-qaf
공식 코드LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
https://github.com/kktsubota/uniform-quantizers
공식 코드Comprehensive Comparisons of Uniform Quantization in Deep Image Compression
https://github.com/kmamine/cam_quant
공식 코드https://github.com/kmheckel/q-S5
공식 코드https://github.com/krafton-ai/lexico
공식 코드Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
https://github.com/kriskrisliu/NoisyQuant
공식 코드NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
https://github.com/kshitij11/pqv-mobile
공식 코드https://github.com/kssteven418/I-BERT
공식 코드https://github.com/kuleshov-group/llmtools
공식 코드ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
https://github.com/kuleshov-group/modulora-experiment
공식 코드ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
https://github.com/kylehkhsu/latent_quantization
공식 코드https://github.com/kylehkhsu/tripod
공식 코드Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning
https://github.com/lab-emi/opendpd
공식 코드OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion
https://github.com/landskape-ai/reprogram_lt
공식 코드https://github.com/langliu95/divergence-frontier-bounds
공식 코드https://github.com/langnatalie/jopeq
공식 코드Joint Privacy Enhancement and Quantization in Federated Learning
https://github.com/lanyunzhu99/Learning-Statistical-Texture-for-Semantic-Segmentation
공식 코드https://github.com/lavieenrose365/autograph
공식 코드An Automatic Graph Construction Framework based on Large Language Models for Recommendation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.