{"list":"other","total":78,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2401.08740","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","created":"2024-01-16","cited_by_count":737},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2303.14389","title":"MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer","created":"2023-03-25","cited_by_count":262},{"id":"2211.09117","title":"MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis","created":"2022-11-16","cited_by_count":227},{"id":"2111.12710","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","created":"2021-11-24","cited_by_count":204},{"id":"2409.04410","title":"Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation","created":"2024-09-06","cited_by_count":155},{"id":"2411.00776","title":"Randomized Autoregressive Visual Generation","created":"2024-11-01","cited_by_count":127},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118},{"id":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112},{"id":"2409.16211","title":"MaskBit: Embedding-free Image Generation via Bit Tokens","created":"2024-09-24","cited_by_count":98},{"id":"2410.01756","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","created":"2024-10-02","cited_by_count":94},{"id":"2412.01827","title":"RandAR: Decoder-only Autoregressive Visual Generation in Random Orders","created":"2024-12-02","cited_by_count":83},{"id":"2305.17997","title":"DiffRate : Differentiable Compression Rate for Efficient Vision Transformers","created":"2023-05-29","cited_by_count":77},{"id":"2103.13027","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","created":"2021-03-24","cited_by_count":69},{"id":"2406.11837","title":"Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%","created":"2024-06-17","cited_by_count":68},{"id":"2412.15119","title":"Parallelized Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":60},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59},{"id":"2306.17842","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","created":"2023-06-30","cited_by_count":55},{"id":"2305.17530","title":"PuMer: Pruning and Merging Tokens for Efficient Vision Language Models","created":"2023-05-27","cited_by_count":53},{"id":"2303.06424","title":"Regularized Vector Quantization for Tokenized Image Synthesis","created":"2023-03-11","cited_by_count":46},{"id":"2411.02393","title":"Adaptive Length Image Tokenization via Recurrent Allocation","created":"2024-11-04","cited_by_count":43},{"id":"2408.01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","created":"2024-08-02","cited_by_count":42},{"id":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39},{"id":"2406.09416","title":"Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization","created":"2024-06-13","cited_by_count":36},{"id":"2302.08899","title":"QARV: Quantization-Aware ResNet VAE for Lossy Image Compression","created":"2023-02-16","cited_by_count":32},{"id":"2503.17076","title":"Halton Scheduler For Masked Generative Image Transformer","created":"2025-03-21","cited_by_count":32},{"id":"2203.15371","title":"mc-BEiT: Multi-choice Discretization for Image BERT Pre-training","created":"2022-03-29","cited_by_count":31},{"id":"2205.13943","title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","created":"2022-05-27","cited_by_count":31},{"id":"2305.13607","title":"Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation","created":"2023-05-23","cited_by_count":28},{"id":"2403.07874","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","created":"2024-03-12","cited_by_count":23},{"id":"2410.12490","title":"Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective","created":"2024-10-16","cited_by_count":22},{"id":"2307.10780","title":"Learned Thresholds Token Merging and Pruning for Vision Transformers","created":"2023-07-20","cited_by_count":21},{"id":"2302.14138","title":"Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations","created":"2023-02-27","cited_by_count":18},{"id":"2411.04406","title":"Image Understanding Makes for A Good Tokenizer for Image Generation","created":"2024-11-07","cited_by_count":15},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13},{"id":"2310.09382","title":"LL-VQ-VAE: Learnable Lattice Vector-Quantization For Efficient Representations","created":"2023-10-13","cited_by_count":4}],"next_cursor":null}