{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177},{"id":"2306.11290","title":"Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation","created":"2023-06-20","cited_by_count":167},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110},{"id":"2306.11565","title":"HomeRobot: Open-Vocabulary Mobile Manipulation","created":"2023-06-20","cited_by_count":106},{"id":"1809.00786","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","created":"2018-09-04","cited_by_count":101},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82},{"id":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77},{"id":"2008.09241","title":"Learning Affordance Landscapes for Interaction Exploration in 3D Environments","created":"2020-08-21","cited_by_count":65},{"id":"2001.02192","title":"An Exploration of Embodied Visual Exploration","created":"2020-01-07","cited_by_count":58},{"id":"2112.00246","title":"AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions","created":"2021-12-01","cited_by_count":57},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57},{"id":"2209.12941","title":"End-to-End Affordance Learning for Robotic Manipulation","created":"2022-09-26","cited_by_count":57},{"id":"2210.00722","title":"GenDexGrasp: Generalizable Dexterous Grasping","created":"2022-10-03","cited_by_count":56},{"id":"2106.15087","title":"O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning","created":"2021-06-29","cited_by_count":46},{"id":"2109.10892","title":"The Design of Stretch: A Compact, Lightweight Mobile Manipulator for Indoor Human Environments","created":"2021-09-22","cited_by_count":40},{"id":"2309.07473","title":"Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects","created":"2023-09-14","cited_by_count":35},{"id":"2209.07147","title":"One-Shot Transfer of Affordance Regions? AffCorrs!","created":"2022-09-15","cited_by_count":31},{"id":"2207.10761","title":"TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors","created":"2022-07-21","cited_by_count":30},{"id":"2212.04819","title":"Phone2Proc: Bringing Robust Robots Into Our Chaotic World","created":"2022-12-08","cited_by_count":26},{"id":"2212.06088","title":"MIRA: Mental Imagery for Robotic Affordances","created":"2022-12-12","cited_by_count":26},{"id":"2207.01971","title":"DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation","created":"2022-07-05","cited_by_count":18},{"id":"2305.17783","title":"Visual Affordance Prediction for Guiding Robot Exploration","created":"2023-05-28","cited_by_count":14}],"next_cursor":null}