{"list":"other","total":111,"rows":[{"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":"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"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},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"1511.06233","title":"Towards Open Set Deep Networks","created":"2015-11-19","cited_by_count":538},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"1901.09192","title":"SelectiveNet: A Deep Neural Network with an Integrated Reject Option","created":"2019-01-26","cited_by_count":350},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"id":"2106.03004","title":"Exploring the Limits of Out-of-Distribution Detection","created":"2021-06-06","cited_by_count":283},{"id":"2112.09127","title":"ICON: Implicit Clothed humans Obtained from Normals","created":"2021-12-16","cited_by_count":283},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2004.04572","title":"ARCH: Animatable Reconstruction of Clothed Humans","created":"2020-04-08","cited_by_count":257},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"id":"1911.10500","title":"Causality for Machine Learning","created":"2019-11-24","cited_by_count":243},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154},{"id":"1509.06113","title":"Deep Spatial Autoencoders for Visuomotor Learning","created":"2015-09-21","cited_by_count":153},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146},{"id":"2204.08906","title":"Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing","created":"2022-04-19","cited_by_count":126},{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117},{"id":"2306.01923","title":"The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation","created":"2023-06-02","cited_by_count":116},{"id":"2502.13967","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","created":"2025-02-19","cited_by_count":110},{"id":"1908.07201","title":"Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images \"In the Wild\"","created":"2019-08-20","cited_by_count":106},{"id":"2403.12365","title":"GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation","created":"2024-03-19","cited_by_count":100},{"id":"1603.02729","title":"Revisiting Active Perception","created":"2016-03-08","cited_by_count":94},{"id":"2401.12963","title":"AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents","created":"2024-01-23","cited_by_count":87},{"id":"2510.03342","title":"Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer","created":"2025-10-02","cited_by_count":87},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70},{"id":"2304.03110","title":"Continual Detection Transformer for Incremental Object Detection","created":"2023-04-06","cited_by_count":59},{"id":"2304.08408","title":"OVTrack: Open-Vocabulary Multiple Object Tracking","created":"2023-04-17","cited_by_count":53},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52},{"id":"2403.08764","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","created":"2024-03-13","cited_by_count":50},{"id":"2205.12256","title":"Differentiable Dynamics for Articulated 3d Human Motion Reconstruction","created":"2022-05-24","cited_by_count":39},{"id":"2403.09623","title":"Score-Guided Diffusion for 3D Human Recovery","created":"2024-03-14","cited_by_count":39},{"id":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34},{"id":"2305.18035","title":"Physics-Informed Computer Vision: A Review and Perspectives","created":"2023-05-29","cited_by_count":28},{"id":"2311.10356","title":"Garment Recovery with Shape and Deformation Priors","created":"2023-11-17","cited_by_count":24},{"id":"2504.14516","title":"Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction","created":"2025-04-20","cited_by_count":24},{"id":"2112.05300","title":"Representing 3D Shapes with Probabilistic Directed Distance Fields","created":"2021-12-10","cited_by_count":21}],"next_cursor":"100"}