{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141},{"id":"2012.04781","title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","created":"2020-12-08","cited_by_count":129},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127},{"id":"2406.08552","title":"DiTFastAttn: Attention Compression for Diffusion Transformer Models","created":"2024-06-12","cited_by_count":115},{"id":"2411.02397","title":"Adaptive Caching for Faster Video Generation with Diffusion Transformers","created":"2024-11-04","cited_by_count":108},{"id":"2305.15805","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","created":"2023-05-25","cited_by_count":67},{"id":"2306.06189","title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","created":"2023-06-09","cited_by_count":65},{"id":"2404.02747","title":"Faster Diffusion via Temporal Attention Decomposition","created":"2024-04-03","cited_by_count":54},{"id":"2411.13503","title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","created":"2024-11-20","cited_by_count":45},{"id":"2211.11167","title":"Vision Transformer with Super Token Sampling","created":"2022-11-21","cited_by_count":44},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43},{"id":"2310.01812","title":"PPT: Token Pruning and Pooling for Efficient Vision Transformers","created":"2023-10-03","cited_by_count":38},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37},{"id":"2310.05719","title":"Transformer Fusion with Optimal Transport","created":"2023-10-09","cited_by_count":36},{"id":"2209.13802","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","created":"2022-09-28","cited_by_count":35},{"id":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34},{"id":"2306.02095","title":"Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers","created":"2023-06-03","cited_by_count":22},{"id":"2311.03233","title":"Navigating Scaling Laws: Compute Optimality in Adaptive Model Training","created":"2023-11-06","cited_by_count":4}],"next_cursor":null}