{"total":1432,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610,"area":"mllm"},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561,"area":null},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528,"area":null},{"id":"2309.17400","title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","created":"2023-09-29","cited_by_count":448,"area":"diffusion"},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446,"area":null},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434,"area":null},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390,"area":null},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"area":null},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363,"area":"mllm"},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330,"area":null},{"id":"2104.08894","title":"The Intrinsic Dimension of Images and Its Impact on Learning","created":"2021-04-18","cited_by_count":315,"area":null},{"id":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312,"area":null},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300,"area":null},{"id":"2105.11120","title":"A Fourier-based Framework for Domain Generalization","created":"2021-05-24","cited_by_count":290,"area":null},{"id":"2303.14420","title":"Human Preference Score: Better Aligning Text-to-Image Models with Human Preference","created":"2023-03-25","cited_by_count":287,"area":"diffusion"},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2203.13333","title":"CLIP-Mesh: Generating textured meshes from text using pretrained image-text models","created":"2022-03-24","cited_by_count":281,"area":null},{"id":"2403.12015","title":"Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation","created":"2024-03-18","cited_by_count":279,"area":"diffusion"},{"id":"2103.12376","title":"Generalizing Face Forgery Detection with High-frequency Features","created":"2021-03-23","cited_by_count":262,"area":null},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258,"area":null},{"id":"2206.08496","title":"Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency","created":"2022-06-17","cited_by_count":250,"area":null},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249,"area":null},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220,"area":"lr"},{"id":"2211.13445","title":"Delving into Out-of-Distribution Detection with Vision-Language Representations","created":"2022-11-24","cited_by_count":216,"area":null},{"id":"2203.06026","title":"The Role of ImageNet Classes in Fr\\'echet Inception Distance","created":"2022-03-11","cited_by_count":213,"area":null},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207,"area":null},{"id":"2306.04675","title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","created":"2023-06-07","cited_by_count":205,"area":"diffusion"},{"id":"2312.09008","title":"Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer","created":"2023-12-11","cited_by_count":196,"area":"diffusion"},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187,"area":null},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185,"area":null},{"id":"2306.09301","title":"OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection","created":"2023-06-15","cited_by_count":179,"area":null},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178,"area":null},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171,"area":null},{"id":"2107.10356","title":"Reading Race: AI Recognises Patient's Racial Identity In Medical Images","created":"2021-07-21","cited_by_count":156,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145,"area":null},{"id":"2303.15233","title":"Text-to-Image Diffusion Models are Zero-Shot Classifiers","created":"2023-03-27","cited_by_count":143,"area":"diffusion"},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133,"area":null},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2203.07740","title":"Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization","created":"2022-03-15","cited_by_count":122,"area":null},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120,"area":null},{"id":"2302.12254","title":"Change is Hard: A Closer Look at Subpopulation Shift","created":"2023-02-23","cited_by_count":120,"area":null},{"id":"2111.13260","title":"NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes","created":"2021-11-25","cited_by_count":119,"area":null},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119,"area":null},{"id":"2101.07296","title":"Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias","created":"2021-01-18","cited_by_count":118,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2206.07045","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","created":"2022-06-14","cited_by_count":117,"area":null},{"id":"2107.01372","title":"Learning Debiased Representation via Disentangled Feature Augmentation","created":"2021-07-03","cited_by_count":116,"area":null},{"id":"2106.11230","title":"Can contrastive learning avoid shortcut solutions?","created":"2021-06-21","cited_by_count":114,"area":null},{"id":"2303.11040","title":"Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving","created":"2023-03-20","cited_by_count":114,"area":null},{"id":"2102.01987","title":"Learning Graph Embeddings for Compositional Zero-shot Learning","created":"2021-02-03","cited_by_count":112,"area":null},{"id":"2101.06046","title":"Counterfactual Generative Networks","created":"2021-01-15","cited_by_count":111,"area":null},{"id":"2106.06047","title":"Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning","created":"2021-06-10","cited_by_count":111,"area":null},{"id":"2202.10103","title":"Robustness and Accuracy Could Be Reconcilable by (Proper) Definition","created":"2022-02-21","cited_by_count":111,"area":null},{"id":"2105.07197","title":"Are Convolutional Neural Networks or Transformers more like human vision?","created":"2021-05-15","cited_by_count":109,"area":null},{"id":"2112.15089","title":"Causal Attention for Interpretable and Generalizable Graph Classification","created":"2021-12-30","cited_by_count":108,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2403.07366","title":"Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors","created":"2024-03-12","cited_by_count":106,"area":null},{"id":"2106.04732","title":"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation","created":"2021-06-08","cited_by_count":104,"area":null},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98,"area":null},{"id":"2102.11273","title":"On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness","created":"2021-02-22","cited_by_count":97,"area":null},{"id":"2205.01491","title":"A Comprehensive Survey of Image Augmentation Techniques for Deep Learning","created":"2022-05-03","cited_by_count":97,"area":null},{"id":"2210.04831","title":"Visual Prompt Tuning for Test-time Domain Adaptation","created":"2022-10-10","cited_by_count":97,"area":null},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95,"area":null},{"id":"2305.00729","title":"What Do Self-Supervised Vision Transformers Learn?","created":"2023-05-01","cited_by_count":93,"area":null},{"id":"2406.05590","title":"NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security","created":"2024-06-08","cited_by_count":93,"area":null},{"id":"2105.05837","title":"When Does Contrastive Visual Representation Learning Work?","created":"2021-05-12","cited_by_count":92,"area":null},{"id":"2303.06873","title":"Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Images","created":"2023-03-13","cited_by_count":91,"area":null},{"id":"2110.13771","title":"AugMax: Adversarial Composition of Random Augmentations for Robust Training","created":"2021-10-26","cited_by_count":90,"area":null},{"id":"2109.05184","title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets","created":"2021-09-11","cited_by_count":86,"area":null},{"id":"2106.07617","title":"Delving Deep into the Generalization of Vision Transformers under Distribution Shifts","created":"2021-06-14","cited_by_count":85,"area":null},{"id":"2206.04046","title":"Sparse Mixture-of-Experts are Domain Generalizable Learners","created":"2022-06-08","cited_by_count":85,"area":"moe"},{"id":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85,"area":null},{"id":"2302.14301","title":"A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking","created":"2023-02-28","cited_by_count":85,"area":null},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2111.02398","title":"Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods","created":"2021-11-01","cited_by_count":83,"area":null},{"id":"2203.15685","title":"EnvEdit: Environment Editing for Vision-and-Language Navigation","created":"2022-03-29","cited_by_count":83,"area":null},{"id":"2209.14107","title":"Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure","created":"2022-09-28","cited_by_count":83,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2108.08782","title":"Causal Attention for Unbiased Visual Recognition","created":"2021-08-19","cited_by_count":80,"area":null},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79,"area":null},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78,"area":null},{"id":"2103.13517","title":"A Broad Study on the Transferability of Visual Representations with Contrastive Learning","created":"2021-03-24","cited_by_count":78,"area":null},{"id":"2203.17260","title":"Generating High Fidelity Data from Low-density Regions using Diffusion Models","created":"2022-03-31","cited_by_count":78,"area":"diffusion"},{"id":"2102.01998","title":"Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond","created":"2021-02-03","cited_by_count":76,"area":null},{"id":"2106.04550","title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","created":"2021-06-08","cited_by_count":76,"area":null},{"id":"2204.00993","title":"Improving Vision Transformers by Revisiting High-frequency Components","created":"2022-04-03","cited_by_count":76,"area":null},{"id":"2212.06727","title":"What do Vision Transformers Learn? A Visual Exploration","created":"2022-12-13","cited_by_count":76,"area":null},{"id":"2402.00045","title":"Detecting Multimedia Generated by Large AI Models: A Survey","created":"2024-01-22","cited_by_count":76,"area":"diffusion"}],"next_cursor":"100"}