Papers with Code 아카이브

Quantization

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/jiangyctarheel/sq-transformer

공식 코드

Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings

https://github.com/jianhayes/nestquant

공식 코드

NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNN

https://github.com/jiaolifengmi/vq-prompt

공식 코드

Vector Quantization Prompting for Continual Learning

https://github.com/jieshibo/petl-vit

공식 코드

Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy

https://github.com/jijunkai/transformer_music

공식 코드

TransMUSIC: A Transformer-Aided Subspace Method for DOA Estimation with Low-Resolution ADCs

https://github.com/jingtaozhan/JPQ

공식 코드

Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance

https://github.com/jingtaozhan/repconc

공식 코드

Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval

https://github.com/jingyangxiang/dfrot

공식 코드

DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation

https://github.com/jishengpeng/languagecodec

공식 코드

Language-Codec: Bridging Discrete Codec Representations and Speech Language Models

https://github.com/jiutian-vl/star

공식 코드

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

https://github.com/jiyoonkm/columnquant

공식 코드

Column-wise Quantization of Weights and Partial Sums for Accurate and Efficient Compute-In-Memory Accelerators

https://github.com/joennlae/halutmatmul

공식 코드

Stella Nera: Achieving 161 TOp/s/W with Multiplier-free DNN Acceleration based on Approximate Matrix Multiplication

https://github.com/johnheo/adadim-llm

공식 코드

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models

https://github.com/jojacola/fuel

공식 코드

Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View

https://github.com/jonahobw/aicas

공식 코드

Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning

https://github.com/jonguti13/parameterprotection

공식 코드

Evaluating Single Event Upsets in Deep Neural Networks for Semantic Segmentation: an embedded system perspective

https://github.com/jonguti13/tensorfi2

공식 코드

Evaluating Single Event Upsets in Deep Neural Networks for Semantic Segmentation: an embedded system perspective

https://github.com/jpeginspireddl/jpeg-inspired-dl

공식 코드

JPEG Inspired Deep Learning

https://github.com/jsjs0369/MEBQAT

공식 코드

Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach

https://github.com/juanerx/q-dit

공식 코드

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers

https://github.com/julianfaraone/SYQ

공식 코드

SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks

https://github.com/juntongkuki/birkhoff-model-compression

공식 코드

Compress Any Segment Anything Model (SAM)

https://github.com/juntongkuki/hyper-compression

공식 코드

Hyper-Compression: Model Compression via Hyperfunction

https://github.com/junyiwucode/quantcache

공식 코드

QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation

https://github.com/junzhang-zj/LoRAM

공식 코드

Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models

https://github.com/jy-yuan/kivi

공식 코드

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

https://github.com/jyonn/cage

공식 코드

Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector Quantization

https://github.com/jyonn/cove

공식 코드

Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector Quantization

https://github.com/k1l1/cocofl

공식 코드

CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization

https://github.com/k2-fsa/icefall

공식 코드

Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation

https://github.com/kai-liu001/2dquant

공식 코드

2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution

https://github.com/kai-liu001/condiquant

공식 코드

CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution

https://github.com/kai-yue/fedvote

공식 코드

Federated Learning via Plurality Vote

https://github.com/kai-yue/predictive-coding-fl

공식 코드

Communication-Efficient Federated Learning via Predictive Coding

https://github.com/kaiqi123/sqakd

공식 코드

Self-Supervised Quantization-Aware Knowledge Distillation

https://github.com/kakaobrain/rq-vae-transformer

공식 코드

Autoregressive Image Generation using Residual Quantization

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.