{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1506.03365","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","created":"2015-06-10","cited_by_count":1355},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2211.01095","title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","created":"2022-11-02","cited_by_count":938},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2202.00273","title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","created":"2022-02-01","cited_by_count":492},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2312.00858","title":"DeepCache: Accelerating Diffusion Models for Free","created":"2023-12-01","cited_by_count":359},{"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":"1911.07013","title":"Understanding and Improving Layer Normalization","created":"2019-11-16","cited_by_count":217},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205},{"id":"2310.01218","title":"Making LLaMA SEE and Draw with SEED Tokenizer","created":"2023-10-02","cited_by_count":185},{"id":"2308.00442","title":"FLatten Transformer: Vision Transformer using Focused Linear Attention","created":"2023-08-01","cited_by_count":171},{"id":"2309.02591","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning","created":"2023-09-05","cited_by_count":170},{"id":"2312.03209","title":"Cache Me if You Can: Accelerating Diffusion Models through Block Caching","created":"2023-12-06","cited_by_count":151},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"2105.15075","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","created":"2021-05-31","cited_by_count":144},{"id":"2307.08041","title":"Planting a SEED of Vision in Large Language Model","created":"2023-07-16","cited_by_count":140},{"id":"1609.02200","title":"Discrete Variational Autoencoders","created":"2016-09-07","cited_by_count":125},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120},{"id":"2411.02359","title":"DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution","created":"2024-11-04","cited_by_count":117},{"id":"2406.02540","title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","created":"2024-06-04","cited_by_count":115},{"id":"2406.08552","title":"DiTFastAttn: Attention Compression for Diffusion Transformer Models","created":"2024-06-12","cited_by_count":115},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102},{"id":"2010.05300","title":"Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification","created":"2020-10-11","cited_by_count":100},{"id":"2012.15833","title":"Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade","created":"2020-12-31","cited_by_count":99},{"id":"2312.08874","title":"Agent Attention: On the Integration of Softmax and Linear Attention","created":"2023-12-14","cited_by_count":90},{"id":"2006.07665","title":"Uncertainty-aware Score Distribution Learning for Action Quality Assessment","created":"2020-06-13","cited_by_count":80},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75},{"id":"2406.11138","title":"Diffusion Models in Low-Level Vision: A Survey","created":"2024-06-17","cited_by_count":74},{"id":"2101.10832","title":"Revisiting Locally Supervised Learning: an Alternative to End-to-end Training","created":"2021-01-26","cited_by_count":71},{"id":"2209.04439","title":"Improved Masked Image Generation with Token-Critic","created":"2022-09-09","cited_by_count":64},{"id":"2303.07820","title":"Adaptive Rotated Convolution for Rotated Object Detection","created":"2023-03-14","cited_by_count":51},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50},{"id":"2306.08860","title":"OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models","created":"2023-06-15","cited_by_count":45},{"id":"2209.08310","title":"Learning to Weight Samples for Dynamic Early-exiting Networks","created":"2022-09-17","cited_by_count":44},{"id":"2405.17873","title":"MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization","created":"2024-05-28","cited_by_count":43},{"id":"2104.04382","title":"CondenseNet V2: Sparse Feature Reactivation for Deep Networks","created":"2021-04-09","cited_by_count":34},{"id":"2206.04452","title":"Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer","created":"2022-06-09","cited_by_count":30},{"id":"2401.14391","title":"Rethinking Patch Dependence for Masked Autoencoders","created":"2024-01-25","cited_by_count":29},{"id":"2308.15949","title":"Latency-aware Unified Dynamic Networks for Efficient Image Recognition","created":"2023-08-30","cited_by_count":26},{"id":"2403.11808","title":"Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation","created":"2024-03-18","cited_by_count":25},{"id":"2408.05710","title":"Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators","created":"2024-08-11","cited_by_count":24},{"id":"2406.05478","title":"Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis","created":"2024-06-08","cited_by_count":22},{"id":"2306.05423","title":"ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process","created":"2023-06-08","cited_by_count":20},{"id":"2405.08768","title":"EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training","created":"2024-05-14","cited_by_count":18},{"id":"2312.07243","title":"A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models","created":"2023-12-12","cited_by_count":14},{"id":"2212.04129","title":"Deep Incubation: Training Large Models by Divide-and-Conquering","created":"2022-12-08","cited_by_count":13},{"id":"2409.00342","title":"AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation","created":"2024-08-31","cited_by_count":13},{"id":"2303.00750","title":"StraIT: Non-autoregressive Generation with Stratified Image Transformer","created":"2023-03-01","cited_by_count":10}],"next_cursor":null}