{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"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},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"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":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2010.03978","title":"A Brief Review of Domain Adaptation","created":"2020-10-07","cited_by_count":288},{"id":"2308.11483","title":"Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions","created":"2023-08-22","cited_by_count":263},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"2206.09426","title":"ADBench: Anomaly Detection Benchmark","created":"2022-06-19","cited_by_count":232},{"id":"2103.01946","title":"Fixing Data Augmentation to Improve Adversarial Robustness","created":"2021-03-02","cited_by_count":204},{"id":"2111.05328","title":"Data Augmentation Can Improve Robustness","created":"2021-11-09","cited_by_count":194},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131},{"id":"2010.08001","title":"Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness","created":"2020-10-15","cited_by_count":121},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119},{"id":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102},{"id":"2102.11273","title":"On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness","created":"2021-02-22","cited_by_count":97},{"id":"2208.05516","title":"Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP","created":"2022-08-10","cited_by_count":97},{"id":"2303.07274","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","created":"2023-03-13","cited_by_count":80},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72},{"id":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64},{"id":"2103.12474","title":"On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors","created":"2021-03-23","cited_by_count":48},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31},{"id":"2305.07528","title":"WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models","created":"2023-05-12","cited_by_count":28},{"id":"2307.12532","title":"On the Connection between Pre-training Data Diversity and Fine-tuning Robustness","created":"2023-07-24","cited_by_count":25},{"id":"2212.08044","title":"Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift","created":"2022-12-15","cited_by_count":24},{"id":"2007.04546","title":"Wandering Within a World: Online Contextualized Few-Shot Learning","created":"2020-07-09","cited_by_count":22},{"id":"2207.00788","title":"Long-Tail Prediction Uncertainty Aware Trajectory Planning for Self-driving Vehicles","created":"2022-07-02","cited_by_count":22},{"id":"2308.12898","title":"Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?","created":"2023-08-24","cited_by_count":21},{"id":"2306.14895","title":"Large Multimodal Models: Notes on CVPR 2023 Tutorial","created":"2023-06-26","cited_by_count":18},{"id":"2006.09512","title":"Visual Chirality","created":"2020-06-16","cited_by_count":14},{"id":"2302.01381","title":"Effective Robustness against Natural Distribution Shifts for Models with Different Training Data","created":"2023-02-02","cited_by_count":13},{"id":"2011.11831","title":"Dissecting Image Crops","created":"2020-11-24","cited_by_count":5},{"id":"2208.12352","title":"OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization","created":"2022-08-25","cited_by_count":5},{"id":"2307.05610","title":"Substance or Style: What Does Your Image Embedding Know?","created":"2023-07-10","cited_by_count":5}],"next_cursor":null}