{"total":5045,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403,"area":null},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968,"area":null},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962,"area":null},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838,"area":null},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627,"area":null},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616,"area":null},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396,"area":null},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322,"area":null},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218,"area":"wm"},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101,"area":null},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057,"area":null},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906,"area":"mllm"},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878,"area":"safety"},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2102.02808","title":"Multi-Stage Progressive Image Restoration","created":"2021-02-04","cited_by_count":816,"area":null},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809,"area":"wm"},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751,"area":null},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723,"area":null},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719,"area":null},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712,"area":null},{"id":"2204.04676","title":"Simple Baselines for Image Restoration","created":"2022-04-10","cited_by_count":708,"area":null},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674,"area":null},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653,"area":null},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651,"area":null},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648,"area":null},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642,"area":null},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627,"area":"mllm"},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622,"area":"driving"},{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600,"area":null},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576,"area":null},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552,"area":null},{"id":"2110.08263","title":"FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","created":"2021-10-15","cited_by_count":540,"area":null},{"id":"2104.04015","title":"CutPaste: Self-Supervised Learning for Anomaly Detection and Localization","created":"2021-04-08","cited_by_count":531,"area":null},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531,"area":null},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528,"area":null},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523,"area":null},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519,"area":null},{"id":"2112.07804","title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","created":"2021-12-15","cited_by_count":516,"area":"diffusion"},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501,"area":null},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459,"area":null},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429,"area":null},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410,"area":null},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2202.07123","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","created":"2022-02-15","cited_by_count":379,"area":null},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365,"area":null},{"id":"2312.13139","title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","created":"2023-12-20","cited_by_count":364,"area":null},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363,"area":null},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360,"area":null},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360,"area":null},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360,"area":null},{"id":"2110.06207","title":"Open-Set Recognition: a Good Closed-Set Classifier is All You Need?","created":"2021-10-12","cited_by_count":353,"area":null},{"id":"2206.01256","title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","created":"2022-06-02","cited_by_count":352,"area":null},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342,"area":null},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329,"area":null},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329,"area":"mllm"},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325,"area":"diffusion"},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317,"area":null},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305,"area":"driving"},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302,"area":null},{"id":"2101.06329","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","created":"2021-01-15","cited_by_count":301,"area":null},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293,"area":null},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291,"area":null},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290,"area":null},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289,"area":null},{"id":"2402.02491","title":"VM-UNet: Vision Mamba UNet for Medical Image Segmentation","created":"2024-02-04","cited_by_count":287,"area":"ssm"},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280,"area":null},{"id":"2303.14968","title":"Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective","created":"2023-03-27","cited_by_count":280,"area":null},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274,"area":null},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274,"area":null},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265,"area":null},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264,"area":null},{"id":"2205.12615","title":"Autoformalization with Large Language Models","created":"2022-05-25","cited_by_count":263,"area":null},{"id":"2204.03883","title":"Vision Transformers for Single Image Dehazing","created":"2022-04-08","cited_by_count":260,"area":null},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259,"area":"distill"},{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256,"area":null},{"id":"2303.09472","title":"DiffIR: Efficient Diffusion Model for Image Restoration","created":"2023-03-16","cited_by_count":255,"area":"diffusion"},{"id":"2111.13802","title":"Factorized Fourier Neural Operators","created":"2021-11-27","cited_by_count":249,"area":null},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2207.12819","title":"S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning","created":"2022-07-26","cited_by_count":246,"area":null},{"id":"2106.14413","title":"Co$^2$L: Contrastive Continual Learning","created":"2021-06-28","cited_by_count":244,"area":null},{"id":"2405.19620","title":"SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation","created":"2024-05-30","cited_by_count":241,"area":"driving"},{"id":"2105.06086","title":"HINet: Half Instance Normalization Network for Image Restoration","created":"2021-05-13","cited_by_count":237,"area":null},{"id":"2110.09468","title":"Improving Robustness using Generated Data","created":"2021-10-18","cited_by_count":234,"area":null},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233,"area":"wm"},{"id":"2303.06705","title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement","created":"2023-03-12","cited_by_count":231,"area":null},{"id":"2204.04662","title":"FOSTER: Feature Boosting and Compression for Class-Incremental Learning","created":"2022-04-10","cited_by_count":229,"area":null}],"next_cursor":"100"}