Kaleido's Personal Page
Article Digests
Pure Alogrithm
Convolutional Networks with Adaptive Inference Graphs
Dynamic Resolution Network
Dynamic Neural Networks: A Survey
Reducing overfitting in deep networks by decorrelating representations
Regularizing cnns with locally constrained decorrelations
U-Net: Convolutional Networks for Biomedical Image Segmentation
Semi-Supervised Classification with Graph Convolutional Networks
A Survey on Vision-Language-Action Models for Embodied AI
CV
3D
3D Classification
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
3D Detection
PointPillars: Fast Encoders for Object Detection from Point Clouds
BackBone
An image is worth 16x16 words: Transformers for image recognition at scale
Image Detection
End-to-End Object Detection with Transformers
LLCV
Image Denoise
Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization
Brief review of image denoising techniques
Toward Convolutional Blind Denoising of Real Photographs
Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latency
Benchmarking Denoising Algorithms with Real Photographs
Deep Learning for Image Denoising： A Survey
Deep Learning on Image Denoising An overview
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Dynamic Residual Dense Network for Image Denoising
Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
Image Blind Denoising With Generative Adversarial Network Based Noise Modeling
HINet： Half Instance Normalization Network for Image Restoration
Learning Deep CNN Denoiser Prior for Image Restoration
Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation
Neural Nearest Neighbors Network
Practical Deep Raw Image Denoising on Mobile Devices
Generalized Deep Image to Image Regression
Real Image Denoising with Feature Attention
Spatial-Adaptive Network for Single Image Denoising
A High-Quality Denoising Dataset for Smartphone Cameras
Robust Image Denoising with Texture-Aware Neural Network
Unprocessing Images for Learned Raw Denoising
Noise2Noise: Learning Image Restoration without Clean Data
Low Light Enhancement
Restoring Extremely Dark Images in Real Time
Learning to See in the Dark
Restoration
CLEARER: Multi-Scale Neural Architecture Search for Image Restoration
CycleISP: Real Image Restoration via Improved Data Synthesis
Deep Image Prior
Learning Enriched Features for Real Image Restoration and Enhancement
Multi-Stage Progressive Image Restoration
MemNet: A Persistent Memory Network for Image Restoration
Self-Guided Network for Fast Image Denoising
Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework
Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising
Attentive Fine-Grained Structured Sparsity for Image Restoration
Restormer: Efficient Transformer for High-Resolution Image Restoration
Uformer: A General U-Shaped Transformer for Image Restoration
Searching for Controllable Image Restoration Networks
Enhanced Image Restoration Via Supervised Target Feature Transfer
Super Resolution
A Layer-Wise Extreme Network Compression for Super Resolution
Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
Binarized Neural Network for Single Image Super Resolution
Fully !antized Image Super-Resolution Networks
PAMS: Quantized Super-Resolution via Parameterized Max Scale
Deep Learning for Image Super-resolution: A Survey
Training Binary Neural Network without Batch Normalization for Image Super-Resolution
Video super‑resolution based on deep learning: a comprehensive survey
BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
Enhanced Deep Residual Networks for Single Image Super-Resolution
Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices
CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution
Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
Adaptive Patch Exiting for Scalable Single Image Super-Resolution
Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search
Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning
Fine-grained neural architecture search for image super-resolution
Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution
DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks
Wide Activation for Efficient and Accurate Image Super-Resolution
Uncategorized
ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo
Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation
Computer Architecture
A Survey of Computer Architecture Simulation Techniques and Tools
DNNAbacus: Toward Accurate Computational Cost Prediction for Deep Neural Networks
MAPLE-Edge: A Runtime Latency Predictor for Edge Devices
STONNE: Enabling Cycle-Level Microarchitectural Simulation for DNN Inference Accelerators
An End-To-End Toolchain: From Automated Cost Modeling to Static WCET and WCEC Analysis
MLPerf Mobile Inference Benchmark
torch. fx: Practical program capture and transformation for deep learning in python
nn-Meter: Towards Accurate Latency Prediction of Deep-Learning Model Inference on Diverse Edge Devices
Energy-Demand Estimation of Embedded Devices Using Deep Artificial Neural Networks
EcoFlow Efficient Convolutional Dataflows on Low-Power Neural Network Accelerators
Embodied AI
Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration
LLM
LORA: LOW-RANK ADAPTATION OF LARGE LAN GUAGE MODELS
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Multi-Agent Frameworks & instances
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversations
CAMEL:Communicative Agents for “Mind” Exploration of Large Language Model Society
RAI Flexible Agent Framework for Embodied AI
Model Compression
GhostNet: More Features from Cheap Operations
MCUNet: Tiny Deep Learning on IoT Devices
MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning
A Survey on Efficient Inference for Large Language Models
深度神经网络压缩与加速综述
BNN related articles
Towards Accurate Binary Convolutional Neural Network
BATS: Binary ArchitecTure Search
Bayesian Optimized 1-Bit CNNs
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Learning Frequency Domain Approximation for Binary Neural Networks
High-Capacity Expert Binary Networks
Learning Channel-wise Interactions for Binary Convolutional Neural Networks
ReCU: Reviving the Dead Weights in Binary Neural Networks
Training Binary Neural Networks with Real-to-Binary Convlutions
Training Binary Neural Networks through Learning with Noisy Supervision
Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
WRPN: Wide Reduced-Precision Networks
XNOR-Net
PokeBNN: A Binary Pursuit of Lightweight Accuracy
ReActNet Towards Precise Binary Neural Network with Generalized Activation Functions
Bitwise Neural Networks
BiT: Robustly Binarized Multi-distilled Transformer
BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations
BoolNet: Minimizing the Energy Consumption of Binary Neural Networks
An Empirical study of Binary Neural Networks’ Optimisation
Deployment
Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latency
Fast Camera Image Denoising on Mobile GPUs with Deep Learning
Kownledge Distillation
A Comprehensive Overhaul of Feature Distillation
Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors
ML System
A systematic methodology for analysis of deep learning hardware and software platforms
Precious: Resource-Demand Estimation for Embedded Neural Network Accelerators
A Learned Performance Model for Tensor Processing Units
Learned TPU Cost Model for XLA Tensor Programs
Efficient Mixed-Precision Large Language Model Inference with TurboMind
NAS
Neural Architecture Search for Dense Prediction Tasks in Computer Vision
A Generic Graph-Based Neural Architecture Encoding Scheme for Predictor-Based NAS
Neural Predictor for Neural Architecture Search
NAS-BENCH-201: Extending the Scope of Reproducible Neural Architecture Search
A Generic Graph-based Neural Architecture Encoding Scheme with Multifaceted Information
Pruning
Architecture-Aware Network Pruning for Vision Quality Applications
Structured Pruning of Neural Networks with Budget-Aware Regularization
ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
Revisiting Random Channel Pruning for Neural Network Compression
DHP: Differentiable Meta Pruning via HyperNetworks
Universally Slimmable Networks and Improved Training Techniques
SLIMMABLE NEURAL NETWORKS
Learning N: M Fine-grained Structured Sparse Neural Networks From Scratch
AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
Quantization
A Survey of Quantization Methods for Efficient Neural Network Inference
Post training 4-bit quantization of convolutional networks for rapid-deployment
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
Up or Down? Adaptive Rounding for Post-Training Quantization
Automated Log-Scale Quantization for Low-Cost Deep Neural Networks
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
Data-Free Quantization Through Weight Equalization and Bias Correction
Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks
Deep Learning with Limited Numerical Precision
Loss Aware Post-training Quantization
Learnable Companding Quantization for Accurate Low-bit Neural Networks
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
Learned Step Size Quantization
MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks
ZeroQ: A Novel Zero Shot Quantization Framework
NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
PACT: Parameterized Clipping Activation for Quantized Neural Networks
Quantization Applications
Post-training Quantization on Diffusion Models
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Quantizable Transformers Removing Outliers by Helping Attention Heads Do Nothing
Q-DM: An Efficient Low-bit Quantized Diffusion Model
Sparsity related articles
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
Unassorted
EsyMo: Scalable and Efficient Deep-Learning Inference on Asymmetric Mobile CPUs
Elf: Accelerate High-resolution Mobile Deep Vision with Content-aware Parallel Offloading
Flexible High-resolution Object Detection on Edge Devices with Tunable Latency
CoDL: Efficient CPU-GPU Co-execution for Deep Learning Inference on Mobile Devices
Melon: Breaking the Memory Wall for Resource-Efficient On-Device Machine Learning
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
Optical Flow Estimation using a Spatial Pyramid Network
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
Codez
AWNAS
Mr.Chen validation exps
2021/4/16 结果反馈与讨论记录
2021/4/30结果反馈与讨论记录
2021/4/9 会议记录
2021/5/19结果反馈与讨论记录
First Charge
2021/6/16结果反馈与讨论记录
2021/6/17实验记录
2021/6/3结果反馈与讨论记录
Comparation between BMXNet & AWNAS
recordings
aw_nas
btcs
layer2
bi_final_model.py
final_model.py
final
bnn_model.py
CNN_model.py
cnn_trainer.md
ops
bnn_ops.py
April Fool
Development Document
nics_fix_pytorch rEADING Record
Requirements
LLM Quantizaiton
LLM Quantizaiton 101
Point Cloud Processing
OpenPCDet
Kitti for 3D Detection
Languages
Python
Enum类
Argparse
defaultdict
logging
Python模块打包相关
tricks
内置函数
Class
Python的杂货知识——Class相关
Decorators
staticmethod
Packets
ipdb
MatPlotLib 画图集锦！
Torch
ctx vs self
nn.Sequential vs nn.ModuleList
nn.avgpool2d
torch.cat
torch.ge、torch.gt、torch.le、torch.lt、torch.eq、torch.equal.
torch.nn.functional.pad
Pytorch的训练过程
Pytorch
Hooks
nn.embedding用法
System Implement
Envi Setup
Ubuntu Setup Instruction
搭建主页的可贵尝试
服务器环境配置(含awnas环境搭建)
Linux Related
BMXNet-V2 building record
tmux
MarkDown related
MarkDown中的分隔线样式
markdown代码块支持的语言
创建MarkDown目录
Page Usage
Avatar Test
Code Blocks
Emoji Test
Fonts Test
Gist Test
Markdown Elements
Mathjax Test
Mentions Test
Mermaid Test
Toasts Card
Primer Utilities Test
Tool Box
Usage of Git
Backups
BNN Related Resources
Progress
2025 Working Progress
2026 Working Progress
Submission Notes
Hardware-Aware Efficient LLCV
Talks & Lectures
PPTs
Talks
21/11/27网管讲计算摄影
21/8/23商汤龚睿昊讲PTQ
21/9/9商汤QAT talk
2022_11_3
2022/8/27 LLCV talk总结
ASP-DAC21 Tutorial
BNN in CVPRW21 0
Image Denoising - Not What You Think
Workshops
AIM2022记录
MAI2022记录
Valse 2021 底层视觉与图像处理Panel
Valse2021
Review
2026/1
ReadMes
Kaleido’s Personal Page
Kaleido’s Personal Page 2022!
Kaleido’s Personal Page 2023!
Kaleido’s Personal Page 2024!
Kaleido’s Personal Page 2025!
Study Record
21/10/2 Learning Log
21/8/26 Learning Log
2022/10/17 TODOs
To Do List
毕业论文记录
素菜积累
Kaleido's Personal Page
articles
ModelCompression
MLSystem
[arxiv2508]Efficient Mixed-Precision Large Language Model Inference with TurboMind.md
Efficient Mixed-Precision Large Language Model Inference with TurboMind
2026/1/26
来源：arxiv2508
Previous
2021-2026,
UCaiJun
Revision
2bda034
Built with
GitHub Pages
using a
theme
provided by
RunDocs
.
Kaleido's Personal Page
master
GitHub
Homepage
Issues
Download
This
Software
is under the terms of
MIT License
.