https://github.com/YannickStruempler/LearnedJPEG
공식 코드Learning to Improve Image Compression without Changing the Standard Decoder
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/Yiming-M/CLIP-EBC
공식 코드CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
https://github.com/Yujun-Shi/BLIP
공식 코드https://github.com/ZeyuLing/MotionLLaMA
공식 코드MotionLLaMA: A Unified Framework for Motion Synthesis and Comprehension
https://github.com/Zhhuizhe/GT-SVQ
공식 코드GT-SVQ: A Linear-Time Graph Transformer for Node Classification Using Spiking Vector Quantization
https://github.com/Zhouaojun/Incremental-Network-Quantization
공식 코드Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
https://github.com/Zi-YuanYang/SCAN-PhysFed
공식 코드https://github.com/ZiweiWangTHU/GMPQ
공식 코드Generalizable Mixed-Precision Quantization via Attribution Rank Preservation
https://github.com/ZiyueHuang/dist-ef-sgdm
공식 코드Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback
https://github.com/a-suozhang/vidit-q
공식 코드https://github.com/aaltoml/nsvqgs
공식 코드Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization
https://github.com/aaltovision/dpqed
공식 코드Differentiable Product Quantization for Memory Efficient Camera Relocalization
https://github.com/aaronhuang-778/billm
공식 코드BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
https://github.com/aaronhuang-778/mc-moe
공식 코드MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More
https://github.com/abdelfattah-lab/razer
공식 코드The Power of Negative Zero: Datatype Customization for Quantized Large Language Models
https://github.com/abdelfattah-lab/shadow_llm
공식 코드ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models
https://github.com/abhijithpunnappurath/a-little-bit-more
공식 코드https://github.com/abhyantrika/nirvana
공식 코드https://github.com/abman23/on-device-llm-wifi-roaming
공식 코드https://github.com/abnervictor/hyperthumbnail
공식 코드Real-time 6K Image Rescaling with Rate-distortion Optimization
https://github.com/adlik/smoothquantplus
공식 코드SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM
https://github.com/adlik/vllm
공식 코드SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM
https://github.com/adreamwu/ptq4dit
공식 코드PTQ4DiT: Post-training Quantization for Diffusion Transformers
https://github.com/aelgabli/fednew
공식 코드FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning
https://github.com/afriesen/ftprop
공식 코드Deep Learning as a Mixed Convex-Combinatorial Optimization Problem
https://github.com/agoncharenko1992/FAT-fast-adjustable-threshold
공식 코드Fast Adjustable Threshold For Uniform Neural Network Quantization (Winning solution of LPIRC-II)
https://github.com/agoncharenko1992/FAT-fast_adjustable_threshold
공식 코드Fast Adjustable Threshold For Uniform Neural Network Quantization (Winning solution of LPIRC-II)
https://github.com/ai-tech-research-lab/nitro-d
공식 코드NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks
https://github.com/ai4ce/loqi-vpr
공식 코드Distillation Improves Visual Place Recognition for Low Quality Images
https://github.com/ai9stars/specmquant
공식 코드Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design
https://github.com/aiha-lab/rilq
공식 코드https://github.com/aiha-lab/tsld
공식 코드Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
https://github.com/ailab-cvc/cv-vae
공식 코드CV-VAE: A Compatible Video VAE for Latent Generative Video Models
https://github.com/air-discover/dqs3d
공식 코드DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection
https://github.com/aisoc-lab/inference-acceleration-bias
공식 코드The Impact of Inference Acceleration Strategies on Bias of LLMs
https://github.com/aispeech-lab/LiMuSE
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.