Papers

This repository documents all the research papers I'm studying throughout my AI/ML learning journey. The list is continuously updated as I progress.

---

• [01] AlexNet: ImageNet Classification with Deep Convolutional Neural Networks
• [02] VGG: Very Deep Convolutional Networks for Large-Scale Image Recognition
• [03] ResNet: Deep Residual Learning for Image Recognition
• [04] R-CNN: Rich feature hierarchies for accurate object detection and semantic segmentation
• [05] Fast R-CNN
• [06] Activation Empirical Evaluation of Rectified Activations in Convolutional Network (ELU/LeakyReLU)
• [07] Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• [08] A Neural Algorithm of Artistic Style
• [09] Activation Searching for Activation Functions (Swish)
• [10] Inception/GoogLeNet: Going Deeper with Convolutions
• [11] EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• [12] Sequence to Sequence Learning with Neural Networks
• [13] Neural Machine Translation by Jointly Learning to Align and Translate
• [14] Generative Adversarial Nets (GAN)
• [15] DCGAN: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• [16] Conditional Generative Adversarial Nets (cGAN)
• [17] Show and Tell: A Neural Image Caption Generator
• [18] Attention Is All You Need
• [19] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• [20] Extracting and Composing Robust Features with Denoising Autoencoders
• [21] GPT-1: Improving Language Understanding by Generative Pre-Training
• [22] Least Squares Generative Adversarial Networks (LSGAN)
• [24] CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• [25] YOLO: You Only Look Once: Unified, Real-Time Object Detection
• [26] ViT: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• [27] Continual Learning Continual Learning with Deep Generative Replay
• [28] Denoising Diffusion Probabilistic Models (DDPM)
• [29] Denoising Diffusion Implicit Models (DDIM)
• [30] CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation
• [31] SentencePiece: A simple and language independent subword tokenizer and detokenizer
• [32] BPE: Neural Machine Translation of Rare Words with Subword Units
• [33] Normalization Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• [34] CartoonGAN: Generative Adversarial Networks for Photo Cartoonization
• [35] Few-Shot Learning Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
• [36] Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization (AdaIN)
• [37] Video-to-Video Synthesis
• [38] FlowNet: Learning Optical Flow with Convolutional Networks
• [39] Auto-Encoding Variational Bayes (VAE)
• [40] U-Net: Convolutional Networks for Biomedical Image Segmentation
• [41] Self-Attention Generative Adversarial Networks (SAGAN)
• [42] Optimizer ADAM: A Method for Stochastic Optimization
• [43] Optimizer Lookahead Optimizer: k steps forward, 1 step back
• [47] DeepSeek-OCR: Context-Aware Visual Text Extraction
• [48] DeepSeek-OCR 2: Visual Causal Flow Scaling for Document Understanding
• [49] Optimizer AdaGrad stepsizes: Sharp convergence over nonconvex landscapes
• [50] Neural Operators DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• [51] Physics-Informed ML Physics-Informed Latent Neural Operator for Real-time Predictions of Complex Physical Systems
• [52] Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs
• [53] Prompt Compression Prompt Compression for Large Language Models: A Survey