{"list":"other","total":108,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"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":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"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":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2010.01083","title":"Integrated Task and Motion Planning","created":"2020-10-02","cited_by_count":290},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2406.10721","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","created":"2024-06-15","cited_by_count":251},{"id":"1806.01242","title":"Graph networks as learnable physics engines for inference and control","created":"2018-06-04","cited_by_count":244},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"1809.10790","title":"Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects","created":"2018-09-27","cited_by_count":241},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2306.14896","title":"RVT: Robotic View Transformer for 3D Object Manipulation","created":"2023-06-26","cited_by_count":225},{"id":"1810.01566","title":"Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids","created":"2018-10-03","cited_by_count":220},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2312.07843","title":"Foundation Models in Robotics: Applications, Challenges, and the Future","created":"2023-12-13","cited_by_count":216},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"2212.08333","title":"AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains","created":"2022-12-16","cited_by_count":208},{"id":"2212.06870","title":"MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare","created":"2022-12-13","cited_by_count":201},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"2309.02561","title":"Physically Grounded Vision-Language Models for Robotic Manipulation","created":"2023-09-05","cited_by_count":165},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161},{"id":"1903.06684","title":"kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation","created":"2019-03-15","cited_by_count":153},{"id":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150},{"id":"1806.08756","title":"Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation","created":"2018-06-22","cited_by_count":142},{"id":"2406.08545","title":"RVT-2: Learning Precise Manipulation from Few Demonstrations","created":"2024-06-12","cited_by_count":137},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136},{"id":"2402.00847","title":"BootsTAP: Bootstrapped Training for Tracking-Any-Point","created":"2024-02-01","cited_by_count":120},{"id":"1612.00341","title":"A Compositional Object-Based Approach to Learning Physical Dynamics","created":"2016-12-01","cited_by_count":119},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103},{"id":"2403.08248","title":"CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models","created":"2024-03-13","cited_by_count":99},{"id":"2308.15975","title":"RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation","created":"2023-08-30","cited_by_count":90},{"id":"2203.05701","title":"6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark","created":"2022-03-11","cited_by_count":86},{"id":"2406.18915","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","created":"2024-06-27","cited_by_count":83},{"id":"2306.14447","title":"RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools","created":"2023-06-26","cited_by_count":76},{"id":"2403.19578","title":"Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics","created":"2024-03-28","cited_by_count":74},{"id":"2009.05085","title":"Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning","created":"2020-09-10","cited_by_count":70},{"id":"1910.11977","title":"KETO: Learning Keypoint Representations for Tool Manipulation","created":"2019-10-26","cited_by_count":69},{"id":"1906.03853","title":"DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions","created":"2019-06-10","cited_by_count":63},{"id":"2105.10389","title":"Learning Visible Connectivity Dynamics for Cloth Smoothing","created":"2021-05-21","cited_by_count":62},{"id":"2310.14386","title":"Learning Generalizable Manipulation Policies with Object-Centric 3D Representations","created":"2023-10-22","cited_by_count":61},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61},{"id":"2103.00589","title":"Learning Symbolic Operators for Task and Motion Planning","created":"2021-02-28","cited_by_count":58},{"id":"2303.13483","title":"NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations","created":"2023-03-23","cited_by_count":57},{"id":"2003.01835","title":"Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data","created":"2020-03-03","cited_by_count":51},{"id":"2211.09786","title":"SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields","created":"2022-11-17","cited_by_count":51},{"id":"1606.02378","title":"SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks","created":"2016-06-08","cited_by_count":49},{"id":"2109.03891","title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation","created":"2021-09-08","cited_by_count":48},{"id":"2211.09325","title":"TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation","created":"2022-11-17","cited_by_count":47},{"id":"2212.00541","title":"Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo","created":"2022-12-01","cited_by_count":47},{"id":"1801.02854","title":"Riemannian Motion Policies","created":"2018-01-09","cited_by_count":46},{"id":"2402.13181","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","created":"2024-02-20","cited_by_count":44},{"id":"2108.04145","title":"Long-Horizon Manipulation of Unknown Objects via Task and Motion Planning with Estimated Affordances","created":"2021-08-09","cited_by_count":40},{"id":"2309.00966","title":"Compositional Diffusion-Based Continuous Constraint Solvers","created":"2023-09-02","cited_by_count":40},{"id":"2406.10788","title":"Physically Embodied Gaussian Splatting: A Realtime Correctable World Model for Robotics","created":"2024-06-16","cited_by_count":40},{"id":"1911.04679","title":"Object-Centric Task and Motion Planning in Dynamic Environments","created":"2019-11-12","cited_by_count":35},{"id":"2310.16035","title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","created":"2023-10-24","cited_by_count":33},{"id":"2406.07549","title":"A3VLM: Actionable Articulation-Aware Vision Language Model","created":"2024-06-11","cited_by_count":33},{"id":"2308.09179","title":"Versatile Multi-Contact Planning and Control for Legged Loco-Manipulation","created":"2023-08-17","cited_by_count":31},{"id":"2106.07643","title":"Unsupervised Learning of Visual 3D Keypoints for Control","created":"2021-06-14","cited_by_count":30},{"id":"2110.00792","title":"Learning Models as Functionals of Signed-Distance Fields for Manipulation Planning","created":"2021-10-02","cited_by_count":29},{"id":"1811.06964","title":"Grasp2Vec: Learning Object Representations from Self-Supervised Grasping","created":"2018-11-16","cited_by_count":27},{"id":"2307.03567","title":"SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networks","created":"2023-07-07","cited_by_count":24},{"id":"2311.00626","title":"nvblox: GPU-Accelerated Incremental Signed Distance Field Mapping","created":"2023-11-01","cited_by_count":24},{"id":"2407.10341","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","created":"2024-07-14","cited_by_count":23},{"id":"2101.11565","title":"Shortest Paths in Graphs of Convex Sets","created":"2021-01-27","cited_by_count":22},{"id":"2306.16700","title":"Dynamic-Resolution Model Learning for Object Pile Manipulation","created":"2023-06-29","cited_by_count":22},{"id":"2205.06333","title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","created":"2022-05-12","cited_by_count":21},{"id":"2302.03573","title":"Local Neural Descriptor Fields: Locally Conditioned Object Representations for Manipulation","created":"2023-02-07","cited_by_count":21},{"id":"2211.01576","title":"Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning","created":"2022-11-03","cited_by_count":19},{"id":"2311.02847","title":"Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs","created":"2023-11-06","cited_by_count":19},{"id":"2312.12791","title":"Model-Based Control with Sparse Neural Dynamics","created":"2023-12-20","cited_by_count":16},{"id":"2009.11852","title":"Learning Equality Constraints for Motion Planning on Manifolds","created":"2020-09-24","cited_by_count":9}],"next_cursor":"100"}