evals

Author: KyleVav

evaluation/data/canon_papers_60.csv

@@ -0,0 +1,61 @@
+Entry,ID,Keywords
+1,https://arxiv.org/abs/1310.4546,Improved Skip-gram
+2,https://arxiv.org/abs/1406.2661,"GAN, Generative Adverserial Networks"
+3,https://arxiv.org/abs/1409.0473,Encoder-Decoder Translation
+4,https://arxiv.org/abs/1409.3215,"seq2seq LSTM, sequence LSTM"
+5,https://arxiv.org/abs/1409.1556,"VGGNet, VGG-Net"
+6,https://arxiv.org/abs/1502.03167,"BatchNorm, Batch Norm, Batch Normalization"
+7,https://arxiv.org/abs/1505.04597,"U-Net, unet"
+8,https://arxiv.org/abs/1512.03385,"ResNet, Residual Network, Residual Paths"
+9,https://arxiv.org/abs/1608.06993,"DenseNet, Dense Neural Network"
+10,https://arxiv.org/abs/1506.02640,"YOLO, You Only Look Once"
+11,https://arxiv.org/abs/1412.6980,"Adam, Adam optimizer"
+12,https://arxiv.org/abs/1706.03762,"Attention, Transformer, Attention Mechanism"
+13,https://arxiv.org/abs/1703.06870,Mask R-CNN
+14,https://arxiv.org/abs/1812.04948,"StyleGAN, style gan, style generative adversial network"
+15,https://arxiv.org/abs/1810.04805,"BERT, Bidirectional Transformer"
+16,https://arxiv.org/abs/1803.03635,"Lottery Ticket Hypothesis, Neural Network Pruning"
+17,https://arxiv.org/abs/2003.08934,"Neural Radiance Field, NeRF"
+18,https://arxiv.org/abs/2010.11929,"Vision Transformer, ViT, "
+19,https://arxiv.org/abs/2001.08361,Scaling Laws
+20,https://arxiv.org/abs/2112.10752,"Latent Diffusion Model, LDM, Latent Diffusion"
+21,https://arxiv.org/abs/1301.3781,"Word2Vec, Bag of word"
+22,https://arxiv.org/abs/1312.6114,"VAE, Variational Autoencoder"
+23,https://arxiv.org/abs/1312.5602,"Atari Reinforcment Learning, Q-learning"
+24,https://arxiv.org/abs/2005.14165,"GPT3, GPT-3"
+25,https://arxiv.org/abs/1807.03039,"Glow, Generative Flow"
+26,https://arxiv.org/abs/2102.12092,DALLE
+27,https://arxiv.org/abs/1907.11692,"RoBERTa, Robust BERT pretraining"
+28,https://arxiv.org/abs/2402.03300,"GRPO, Deepseek Math"
+29,https://arxiv.org/abs/2203.02155,"RLHF, InstructGPT"
+30,https://arxiv.org/abs/2103.00020,"CLIP, Contrastive Language Image Pretraining"
+31,https://arxiv.org/abs/2103.14030,"SWIN, SWIN Transformer, Shifted Windows "
+32,https://arxiv.org/abs/2204.02311,"PaLM, Pathways Language Model"
+33,https://arxiv.org/abs/2004.10934,YOLOv4
+34,https://arxiv.org/abs/1910.10683,"T5, text-to-text transformer"
+35,https://arxiv.org/abs/2204.08583,"VQGAN, vector quantized gan, vector quantized generative adverserial network"
+36,https://arxiv.org/abs/1611.07004,"pix2pix, cGAN image to image, PatchGAN discrimnator"
+37,https://arxiv.org/abs/1707.06347,"PPO, Proximal Policy Optimization"
+38,https://arxiv.org/abs/2111.06377,"MAE, Masked AE, Masked Autoencoder"
+39,https://arxiv.org/abs/1409.4842,"Inception, Inceptionv1, Inception CNN"
+40,https://arxiv.org/abs/1602.07261,Inceptionv4
+41,https://arxiv.org/abs/1512.00567,Inceptionv3
+42,https://arxiv.org/abs/1406.1078,"GRU, Gated Recurrent Unit"
+43,https://arxiv.org/abs/1411.4038,"FCN, fully convolution network"
+44,https://arxiv.org/abs/2304.07193,"DINOv2, improved self distillation with no labels"
+45,https://arxiv.org/abs/2104.14294,"DINO, self-distillation with no labels"
+46,https://arxiv.org/abs/2312.00752,mamba
+47,https://arxiv.org/abs/2106.09685,"LoRA, low rank adaptation, low rank adapter"
+48,https://arxiv.org/abs/2305.14314,"QLoRA, quantized lora, quantized low rank adapter"
+49,https://arxiv.org/abs/2205.14135,"FlashAttention, Flash Attention"
+50,https://arxiv.org/abs/2304.02643,"SAM, segment anything, segment anything model"
+51,https://arxiv.org/abs/2302.05543,"ControlNET, "
+52,https://arxiv.org/abs/2303.08774,"GPT4, GPT-4, openai gpt"
+53,https://arxiv.org/abs/2005.11401,"rag, retrieval augmented generation"
+54,https://arxiv.org/abs/1910.01108,"DistilBert, distilled bert"
+55,https://arxiv.org/abs/1802.05365,"ELMo, embeddings from language model"
+56,https://arxiv.org/abs/1711.00937,"vq-vae, vector quantized vae, vector quantized variational autoencoder"
+57,https://arxiv.org/abs/2006.11239,"Diffusion Probabalistic Model, Denoising Diffusion Probabalistic, Diffusion Probabalistic, DDPM"
+58,https://arxiv.org/abs/2010.02502,"Difussion Implicit Model, Denosining Diffusion Implcit, Diffusion Implicit, DDIM"
+59,https://arxiv.org/abs/1701.07875,"WGAN, Wassterstein GAN"
+60,https://arxiv.org/abs/1709.01507,"SE block, SE layer, Squeeze-and-Excitation"