{"list":"other","total":86,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"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":"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":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"1603.02199","title":"Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection","created":"2016-03-07","cited_by_count":316},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2306.17582","title":"ChatGPT for Robotics: Design Principles and Model Abilities","created":"2023-02-20","cited_by_count":299},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"1703.09312","title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","created":"2017-03-27","cited_by_count":264},{"id":"1905.10520","title":"6-DOF GraspNet: Variational Grasp Generation for Object Manipulation","created":"2019-05-25","cited_by_count":242},{"id":"1509.06825","title":"Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours","created":"2015-09-23","cited_by_count":209},{"id":"2112.03145","title":"Diffusion Models for Implicit Image Segmentation Ensembles","created":"2021-12-06","cited_by_count":198},{"id":"2011.08641","title":"A Review of Generalized Zero-Shot Learning Methods","created":"2020-11-17","cited_by_count":159},{"id":"2304.01852","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","created":"2023-04-04","cited_by_count":154},{"id":"2211.16431","title":"NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360{\\deg} Views","created":"2022-11-29","cited_by_count":148},{"id":"1804.05172","title":"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach","created":"2018-04-14","cited_by_count":120},{"id":"2011.09584","title":"ACRONYM: A Large-Scale Grasp Dataset Based on Simulation","created":"2020-11-18","cited_by_count":117},{"id":"1301.3592","title":"Deep Learning for Detecting Robotic Grasps","created":"2013-01-16","cited_by_count":116},{"id":"2104.01542","title":"Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations","created":"2021-04-04","cited_by_count":108},{"id":"1803.11469","title":"Jacquard: A Large Scale Dataset for Robotic Grasp Detection","created":"2018-03-30","cited_by_count":87},{"id":"1809.06267","title":"PointNetGPD: Detecting Grasp Configurations from Point Sets","created":"2018-09-17","cited_by_count":80},{"id":"2304.12654","title":"CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis","created":"2023-04-25","cited_by_count":78},{"id":"2207.02556","title":"Deep Learning Approaches to Grasp Synthesis: A Review","created":"2022-07-06","cited_by_count":72},{"id":"2206.08522","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","created":"2022-06-17","cited_by_count":68},{"id":"2003.01314","title":"EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation","created":"2020-03-03","cited_by_count":61},{"id":"1909.04810","title":"Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network","created":"2019-09-11","cited_by_count":59},{"id":"2303.08622","title":"Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer","created":"2023-03-15","cited_by_count":59},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51},{"id":"2109.09163","title":"CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation","created":"2021-09-19","cited_by_count":49},{"id":"2107.05287","title":"End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB","created":"2021-07-12","cited_by_count":44},{"id":"2303.02401","title":"Open-Vocabulary Affordance Detection in 3D Point Clouds","created":"2023-03-04","cited_by_count":41},{"id":"2302.12610","title":"A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter","created":"2023-02-24","cited_by_count":34},{"id":"2309.09818","title":"Grasp-Anything: Large-scale Grasp Dataset from Foundation Models","created":"2023-09-18","cited_by_count":33},{"id":"2108.11092","title":"INVIGORATE: Interactive Visual Grounding and Grasping in Clutter","created":"2021-08-25","cited_by_count":32},{"id":"1808.10313","title":"ROI-based Robotic Grasp Detection for Object Overlapping Scenes","created":"2018-08-30","cited_by_count":31},{"id":"1912.05604","title":"A Billion Ways to Grasp: An Evaluation of Grasp Sampling Schemes on a Dense, Physics-based Grasp Data Set","created":"2019-12-11","cited_by_count":30},{"id":"2012.03515","title":"Fine-grained Angular Contrastive Learning with Coarse Labels","created":"2020-12-07","cited_by_count":30},{"id":"2203.08037","title":"Interactive Robotic Grasping with Attribute-Guided Disambiguation","created":"2022-03-15","cited_by_count":19},{"id":"2308.10157","title":"Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction","created":"2023-08-20","cited_by_count":18},{"id":"2307.14392","title":"Human-centric Scene Understanding for 3D Large-scale Scenarios","created":"2023-07-26","cited_by_count":17},{"id":"2310.18986","title":"Controllable Group Choreography using Contrastive Diffusion","created":"2023-10-29","cited_by_count":17},{"id":"2004.09805","title":"AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification","created":"2020-04-21","cited_by_count":14},{"id":"2208.03963","title":"MetaGraspNet: A Large-Scale Benchmark Dataset for Scene-Aware Ambidextrous Bin Picking via Physics-based Metaverse Synthesis","created":"2022-08-08","cited_by_count":13},{"id":"2304.09448","title":"EC^2: Emergent Communication for Embodied Control","created":"2023-04-19","cited_by_count":10},{"id":"2310.15948","title":"Language-driven Scene Synthesis using Multi-conditional Diffusion Model","created":"2023-10-24","cited_by_count":10},{"id":"2211.04275","title":"Machine Learning-based Framework for Optimally Solving the Analytical Inverse Kinematics for Redundant Manipulators","created":"2022-11-08","cited_by_count":9},{"id":"2205.10529","title":"Fine-Grained Visual Classification using Self Assessment Classifier","created":"2022-05-21","cited_by_count":8},{"id":"2211.04895","title":"Grasp Learning: Models, Methods, and Performance","created":"2022-11-09","cited_by_count":8},{"id":"2211.02516","title":"Singularity Avoidance with Application to Online Trajectory Optimization for Serial Manipulators","created":"2022-11-04","cited_by_count":7},{"id":"2304.01515","title":"Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models","created":"2023-04-04","cited_by_count":6},{"id":"2304.02893","title":"Object-centric Inference for Language Conditioned Placement: A Foundation Model based Approach","created":"2023-04-06","cited_by_count":4},{"id":"2306.10265","title":"NBMOD: Find It and Grasp It in Noisy Background","created":"2023-06-17","cited_by_count":3},{"id":"2308.09599","title":"Language-Guided Diffusion Model for Visual Grounding","created":"2023-08-18","cited_by_count":3}],"next_cursor":null}