# Book_論文翻譯
###### tags: `book`
神經網路相關論文翻譯
LLM
---
- [Attention Is All You Need](https://hackmd.io/@shaoeChen/BkxGXkS96)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://hackmd.io/@shaoeChen/r1UWj4XYkx)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://hackmd.io/@shaoeChen/BkjbSpWcye)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention(機翻未調校)](https://hackmd.io/@shaoeChen/H1G6azXqye)
- [OUTRAGEOUSLY LARGE NEURAL NETWORKS: THE SPARSELY-GATED MIXTURE-OF-EXPERTS LAYER(機翻未調校)](https://hackmd.io/@shaoeChen/rk_eqe4c1g)
GAN
---
- [DCGANs_Paper(翻譯)](https://hackmd.io/@shaoeChen/B1_b6g3WS)
- [WGAN_Paper(翻譯)](https://hackmd.io/@shaoeChen/ryT0HZtXr)
- [Improved Training of Wasserstein GANs_Paper(翻譯)](https://hackmd.io/@shaoeChen/H1fpco3rB)
- [Wasserstein GAN and the Kantorovich-Rubinstein Duality(翻譯)](https://hackmd.io/@shaoeChen/H1pT3o2Br)
- [A Wasserstein GAN model with the total variational regularization(翻譯)](https://hackmd.io/@shaoeChen/Sk5tnUByO)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation(翻譯)](https://hackmd.io/@shaoeChen/ryIH43v9n)
- [A Style-Based Generator Architecture for Generative Adversarial Networks(翻譯)](https://hackmd.io/@shaoeChen/r1DOGOSCp)
- [Analyzing and Improving the Image Quality of StyleGAN(翻譯)](https://hackmd.io/@shaoeChen/rJWBrzae0)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks(翻譯)](https://hackmd.io/@shaoeChen/BkMuLJNPR)
- [Image-to-Image Translation with Conditional Adversarial Networks(翻譯)](https://hackmd.io/@shaoeChen/HJ-UN4fO0)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution(翻譯)](https://hackmd.io/@shaoeChen/r1fHVEzO0)
Stable Diffusion
---
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://hackmd.io/@shaoeChen/HkPV-K4PJe)
RL
---
- [Ride-Hailing Order Dispatching at DiDi via Reinforcement Learning(1)(翻譯)](https://hackmd.io/@shaoeChen/r1T5dCzVO)
- [Ride-Hailing Order Dispatching at DiDi via Reinforcement Learning(2)(翻譯)](https://hackmd.io/@shaoeChen/r1Q6TzyHO)
- [Ride-Hailing Order Dispatching at DiDi via Reinforcement Learning(Appendix)(翻譯)](https://hackmd.io/@shaoeChen/r1YO_Rz8d)
- [A Deep Value-network Based Approach for Multi-Driver Order Dispatching(翻譯)](https://hackmd.io/@shaoeChen/S1sRFzzuc)
- [Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning(1)](https://hackmd.io/@shaoeChen/Hy48RPzwO)
- [Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning(2)](https://hackmd.io/@shaoeChen/HyHRHiD6K)
- [Learning Options in Reinforcement Learning(翻譯中)(放生)](https://hackmd.io/@shaoeChen/SkEUDfqJ9)
- [A Reinforcement Learning Environment For Job-Shop Scheduling(翻譯)](https://hackmd.io/@shaoeChen/S1UmWvfN9)
- [Actor-Critic Algorithms](https://hackmd.io/@shaoeChen/BJvQl5Zq5)
- [DQN]
- [Soft Actor-Critic]
CNN
---
- [Gradient-Based Learning Applied to Document Recognition_Paper(LeNet-5)(翻譯)(I, II)](https://hackmd.io/@shaoeChen/rJvD_alOS)
- [Gradient-Based Learning Applied to Document Recognition_Paper(LeNet-5)(翻譯)(III, IV)](https://hackmd.io/@shaoeChen/B1gid86cB)
- [Gradient-Based Learning Applied to Document Recognition_Paper(LeNet-5)(翻譯)(V, VI)](https://hackmd.io/@shaoeChen/SyjI6W2zB)
- [Gradient-Based Learning Applied to Document Recognition_Paper(LeNet-5)(翻譯)(VII, VIII)](https://hackmd.io/@shaoeChen/SyGkzHge8)
- [Gradient-Based Learning Applied to Document Recognition_Paper(LeNet-5)(翻譯)(IX)](https://hackmd.io/@shaoeChen/ry4vJ7lG8)
- [Gradient-Based Learning Applied to Document Recognition_Paper(LeNet-5)(翻譯)(X)](https://hackmd.io/@shaoeChen/SyGIGnUM8)
- [Gradient-Based Learning Applied to Document Recognition_Paper(LeNet-5)(翻譯)(XI)](https://hackmd.io/@shaoeChen/ryu_wMKML)
- [ImageNet Classification with Deep Convolutional Neural Networks(AlexNet)(翻譯)](https://hackmd.io/@shaoeChen/SJK_0YJmI)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition(VGG16)(翻譯)](https://hackmd.io/@shaoeChen/BJ2DMA7QU)
- [Going deeper with convolutions(Inception-v1)(翻譯))](https://hackmd.io/@shaoeChen/rkIGBzWEI)
- [Rethinking the Inception Architecture for Computer Vision(Inception-v2)](https://arxiv.org/abs/1512.00567)
- [Network In Network(翻譯)](https://hackmd.io/@shaoeChen/HJ19NfW4U)
- [Deep Residual Learning for Image Recognition(ResNet)(翻譯)](https://hackmd.io/@shaoeChen/Sy_e1mCEU)
- [Identity Mappings in Deep Residual Networks(翻譯)](https://hackmd.io/@shaoeChen/HkRA9oxLI)
- [CSPNET: A NEW BACKBONE THAT CAN ENHANCE LEARNING CAPABILITY OF CNN(翻譯)](https://hackmd.io/@shaoeChen/S1hSH4Dvj)
Visualization
---
- [Visualizing and Understanding Convolutional Networks(翻譯)\_wait](https://hackmd.io/@shaoeChen/BkJPNfWN8)
Object Detection
---
- [You Only Look Once: Unified, Real-Time Object Detection(YOLOv1)(翻譯)](https://hackmd.io/@shaoeChen/Hy6kUMWNI)
- [YOLO9000: Better, Faster, Stronger(YOLOv2)(翻譯)](https://hackmd.io/@shaoeChen/r1TTbG2OL)
- [YOLOv3: An Incremental Improvement(翻譯)](https://hackmd.io/@shaoeChen/ryHg904h9)
- [YOLOv3實作整理](https://hackmd.io/@shaoeChen/HkrRPNGas)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection(翻譯)](https://hackmd.io/@shaoeChen/Skiym0XEi)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors]
Face Recognition
---
- [ArcFace: Additive Angular Margin Loss for Deep Face Recognition(翻譯)](https://hackmd.io/@shaoeChen/S1SZAZwg1g)
Semantic Segmentation
---
- [Fully Convolutional Networks for Semantic Segmentation(翻譯)](https://hackmd.io/@shaoeChen/BJB0NfZVL)
Knowledge Distillation
---
- [Distilling the knowledge in a neural network(翻譯)](https://hackmd.io/@shaoeChen/Hyn9Udkja)
ML
---
- [Efficient and Robust Automated Machine Learning](https://proceedings.neurips.cc/paper_files/paper/2015/file/11d0e6287202fced83f79975ec59a3a6-Paper.pdf)
Trick
---
- [Instance Normalization: The Missing Ingredient for Fast Stylization(翻譯)](https://hackmd.io/@shaoeChen/H1O6dP5lA)
待讀論文
---
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks_wait]()
- [FGSM](https://arxiv.org/abs/1412.6572)
- [Basic iterative method](https://arxiv.org/abs/1607.02533)
- [L-BFGS](https://arxiv.org/abs/1312.6199)
- [Deepfool](https://arxiv.org/abs/1511.04599)
- [JSMA](https://arxiv.org/abs/1511.07528)
- [C&W](https://arxiv.org/abs/1608.04644)
- [Elastic net attac](https://arxiv.org/abs/1709.04114)
- [Spatially Transformed](https://arxiv.org/abs/1801.02612)
- [One Picel Attack](https://arxiv.org/abs/1710.08864)
- [Object Detection Networks on Convolutional Feature Maps_\wait]
- [Understanding the difficulty of training deep feedforward neural networks(翻譯)\_wait](https://hackmd.io/@shaoeChen/SkpxEfZVL)
- [Residual Networks Behave Like Ensembles of Relatively Shallow Networks(翻譯)_\wait](https://hackmd.io/@shaoeChen/B1gbP9bLL)
- [Squeeze-and-Excitation Networks(SENet)(翻譯\_wait)](https://arxiv.org/pdf/1709.01507.pdf)
- [Selective Kernel Networks(SKNet)(翻譯)\_wait](https://arxiv.org/abs/1903.06586)
- [Mistral 7B](https://arxiv.org/pdf/2310.06825.pdf)
- [Mixtral of Experts](https://arxiv.org/pdf/2401.04088.pdf)
- [PhotoMaker](https://arxiv.org/pdf/2312.04461.pdf)
- [Stable Code 3B]()
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://arxiv.org/pdf/2401.09417.pdf)
- [Self-Rewarding Language Models](https://arxiv.org/abs/2401.10020)
- [I2V-Adapter: A General Image-to-Video Adapter for Video Diffusion Models](https://arxiv.org/pdf/2312.16693.pdf)
- [TinyLlama: An Open-Source Small Language Model](https://arxiv.org/pdf/2401.02385.pdf)
- [MEDUSA: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://arxiv.org/pdf/2401.10774.pdf)
- [FitNets: Hints for Thin Deep Nets]
- [Knowledge distillation for natural language processing.]
- [A survey on knowledge distillation]
- [Knowledge distillation: A survey of recent advances.]
- [Knowledge distillation for computer vision.]
- [ALOHA2](https://aloha-2.github.io/assets/aloha2.pdf)
- [YOLOv9](https://arxiv.org/pdf/2402.13616.pdf)
- [Stable Cascade](https://stability.ai/news/introducing-stable-cascade)
- [GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection](https://arxiv.org/abs/2403.03507)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://stabilityai-public-packages.s3.us-west-2.amazonaws.com/Stable+Diffusion+3+Paper.pdf)
- [Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention](https://arxiv.org/pdf/2404.07143.pdf)
- [Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis](https://arxiv.org/abs/2404.13686)
- [Diffusion Models for Video Generation(文章)](https://lilianweng.github.io/posts/2024-04-12-diffusion-video/)
- [What are Diffusion Models?(文章)](https://lilianweng.github.io/posts/2021-07-11-diffusion-models/)
- [Attention as an RNN](https://arxiv.org/pdf/2405.13956)
- [YOLOv10](https://arxiv.org/pdf/2405.14458)