{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"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":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1901.02970","title":"Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation","created":"2019-01-09","cited_by_count":495},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"2311.07885","title":"One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion","created":"2023-11-14","cited_by_count":283},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195},{"id":"2307.14460","title":"MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation","created":"2023-07-26","cited_by_count":174},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165},{"id":"2310.12921","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","created":"2023-10-19","cited_by_count":165},{"id":"2305.10626","title":"Language Models Meet World Models: Embodied Experiences Enhance Language Models","created":"2023-05-18","cited_by_count":124},{"id":"2204.10776","title":"Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images","created":"2022-04-22","cited_by_count":121},{"id":"2311.15707","title":"SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation","created":"2023-11-27","cited_by_count":117},{"id":"2311.16090","title":"Self-correcting LLM-controlled Diffusion Models","created":"2023-11-27","cited_by_count":113},{"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":"2007.13866","title":"se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains","created":"2020-07-27","cited_by_count":90},{"id":"2211.12498","title":"Touch and Go: Learning from Human-Collected Vision and Touch","created":"2022-11-22","cited_by_count":87},{"id":"2307.11067","title":"CNOS: A Strong Baseline for CAD-based Novel Object Segmentation","created":"2023-07-20","cited_by_count":87},{"id":"2212.03239","title":"Perspective Fields for Single Image Camera Calibration","created":"2022-12-06","cited_by_count":75},{"id":"2207.13691","title":"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization","created":"2022-07-27","cited_by_count":72},{"id":"2307.11073","title":"OBJECT 3DIT: Language-guided 3D-aware Image Editing","created":"2023-07-20","cited_by_count":63},{"id":"2110.11590","title":"DIML/CVL RGB-D Dataset: 2M RGB-D Images of Natural Indoor and Outdoor Scenes","created":"2021-10-22","cited_by_count":46},{"id":"2309.09969","title":"Prompt a Robot to Walk with Large Language Models","created":"2023-09-18","cited_by_count":45},{"id":"2203.01072","title":"OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimation","created":"2022-03-02","cited_by_count":43},{"id":"2312.09738","title":"3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V","created":"2023-12-15","cited_by_count":15},{"id":"2304.07537","title":"Gradient-less Federated Gradient Boosting Trees with Learnable Learning Rates","created":"2023-04-15","cited_by_count":12},{"id":"2305.11236","title":"Efficient Vertical Federated Learning with Secure Aggregation","created":"2023-05-18","cited_by_count":3}],"next_cursor":null}