{"total":921,"rows":[{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681,"area":null},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819,"area":null},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449,"area":null},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436,"area":null},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336,"area":null},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304,"area":null},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294,"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":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266,"area":null},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262,"area":null},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261,"area":null},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255,"area":null},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251,"area":null},{"id":"2105.14517","title":"GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning","created":"2021-05-30","cited_by_count":228,"area":null},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221,"area":null},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"area":null},{"id":"2111.01007","title":"Projected GANs Converge Faster","created":"2021-11-01","cited_by_count":208,"area":null},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163,"area":null},{"id":"2210.02885","title":"RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank","created":"2022-10-05","cited_by_count":153,"area":null},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147,"area":null},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"area":null},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147,"area":null},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136,"area":null},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135,"area":null},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133,"area":null},{"id":"2104.00670","title":"Unconstrained Scene Generation with Locally Conditioned Radiance Fields","created":"2021-04-01","cited_by_count":130,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":126,"area":null},{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123,"area":null},{"id":"2207.07039","title":"Convolutional Bypasses Are Better Vision Transformer Adapters","created":"2022-07-14","cited_by_count":121,"area":null},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120,"area":null},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120,"area":null},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","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":"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":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2104.00587","title":"NeRF-VAE: A Geometry Aware 3D Scene Generative Model","created":"2021-04-01","cited_by_count":112,"area":null},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104,"area":null},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104,"area":null},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102,"area":null},{"id":"2101.12609","title":"Open World Compositional Zero-Shot Learning","created":"2021-01-29","cited_by_count":101,"area":null},{"id":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101,"area":null},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","cited_by_count":95,"area":null},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2106.05963","title":"Learning to See by Looking at Noise","created":"2021-06-10","cited_by_count":92,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90,"area":null},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90,"area":null},{"id":"2107.03438","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","created":"2021-07-07","cited_by_count":89,"area":null},{"id":"2104.01148","title":"Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation","created":"2021-04-02","cited_by_count":88,"area":null},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"area":null},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","cited_by_count":85,"area":null},{"id":"2302.12022","title":"DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule","created":"2023-02-08","cited_by_count":85,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2201.03529","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","created":"2022-01-10","cited_by_count":83,"area":null},{"id":"2302.12247","title":"Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework","created":"2023-02-23","cited_by_count":83,"area":null},{"id":"2511.13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models","created":"2025-11-17","cited_by_count":82,"area":null},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80,"area":null},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79,"area":null},{"id":"2201.13100","title":"Adversarial Masking for Self-Supervised Learning","created":"2022-01-31","cited_by_count":78,"area":null},{"id":"2104.05832","title":"SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning","created":"2021-04-12","cited_by_count":77,"area":null},{"id":"2211.13319","title":"Make-A-Story: Visual Memory Conditioned Consistent Story Generation","created":"2022-11-23","cited_by_count":76,"area":null},{"id":"2204.13226","title":"Offline Visual Representation Learning for Embodied Navigation","created":"2022-04-27","cited_by_count":75,"area":null},{"id":"2209.06192","title":"StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation","created":"2022-09-13","cited_by_count":74,"area":null},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73,"area":null},{"id":"2111.09297","title":"Learning to Compose Visual Relations","created":"2021-11-17","cited_by_count":72,"area":null},{"id":"2104.03149","title":"Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering","created":"2021-04-07","cited_by_count":71,"area":null},{"id":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2303.14773","title":"BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning","created":"2023-03-26","cited_by_count":70,"area":null},{"id":"2307.08689","title":"COLLIE: Systematic Construction of Constrained Text Generation Tasks","created":"2023-07-17","cited_by_count":70,"area":null},{"id":"2308.08428","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","created":"2023-08-16","cited_by_count":70,"area":null},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"area":null},{"id":"2203.04571","title":"A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices","created":"2022-03-09","cited_by_count":64,"area":null},{"id":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64,"area":null},{"id":"2202.11855","title":"Learning Multi-Object Dynamics with Compositional Neural Radiance Fields","created":"2022-02-24","cited_by_count":63,"area":null},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63,"area":null},{"id":"2307.11073","title":"OBJECT 3DIT: Language-guided 3D-aware Image Editing","created":"2023-07-20","cited_by_count":63,"area":null},{"id":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62,"area":null},{"id":"2212.11984","title":"DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis","created":"2022-12-22","cited_by_count":61,"area":null},{"id":"2303.09166","title":"Identifiability Results for Multimodal Contrastive Learning","created":"2023-03-16","cited_by_count":61,"area":null},{"id":"2311.17055","title":"No Representation Rules Them All in Category Discovery","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2110.10189","title":"StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects","created":"2021-10-19","cited_by_count":59,"area":null}],"next_cursor":"100"}