{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2010.03409","title":"Learning Mesh-Based Simulation with Graph Networks","created":"2020-10-07","cited_by_count":868},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"1912.03263","title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","created":"2019-12-06","cited_by_count":405},{"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":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1603.06393","title":"Incorporating Copying Mechanism in Sequence-to-Sequence Learning","created":"2016-03-21","cited_by_count":218},{"id":"1602.03264","title":"A Theory of Generative ConvNet","created":"2016-02-10","cited_by_count":174},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1601.01280","title":"Language to Logical Form with Neural Attention","created":"2016-01-06","cited_by_count":158},{"id":"1903.06684","title":"kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation","created":"2019-03-15","cited_by_count":153},{"id":"1511.02793","title":"Generating Images from Captions with Attention","created":"2015-11-09","cited_by_count":136},{"id":"2012.01316","title":"Improved Contrastive Divergence Training of Energy Based Models","created":"2020-12-02","cited_by_count":130},{"id":"2112.08879","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","created":"2021-12-16","cited_by_count":128},{"id":"2210.02438","title":"DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics","created":"2022-10-05","cited_by_count":106},{"id":"2104.03311","title":"PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics","created":"2021-04-07","cited_by_count":103},{"id":"2012.07277","title":"Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs","created":"2020-12-14","cited_by_count":83},{"id":"1811.00090","title":"SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning","created":"2018-10-31","cited_by_count":78},{"id":"2012.03385","title":"Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks","created":"2020-12-06","cited_by_count":78},{"id":"2007.02168","title":"Scalable Differentiable Physics for Learning and Control","created":"2020-07-04","cited_by_count":73},{"id":"2111.09297","title":"Learning to Compose Visual Relations","created":"2021-11-17","cited_by_count":72},{"id":"2002.09253","title":"Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration","created":"2020-02-21","cited_by_count":68},{"id":"1809.11169","title":"Propagation Networks for Model-Based Control Under Partial Observation","created":"2018-09-28","cited_by_count":64},{"id":"2110.10189","title":"StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects","created":"2021-10-19","cited_by_count":59},{"id":"1907.05518","title":"Graph-Structured Visual Imitation","created":"2019-07-11","cited_by_count":43},{"id":"2303.02346","title":"FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation","created":"2023-03-04","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":"1909.06878","title":"Model Based Planning with Energy Based Models","created":"2019-09-15","cited_by_count":33},{"id":"2209.00465","title":"On Grounded Planning for Embodied Tasks with Language Models","created":"2022-08-29","cited_by_count":33},{"id":"1909.13072","title":"Regression Planning Networks","created":"2019-09-28","cited_by_count":32},{"id":"2103.09439","title":"HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks","created":"2021-03-17","cited_by_count":18},{"id":"1811.02486","title":"Concept Learning with Energy-Based Models","created":"2018-11-06","cited_by_count":14},{"id":"1904.05453","title":"Energy-Based Continuous Inverse Optimal Control","created":"2019-04-10","cited_by_count":14},{"id":"2202.10765","title":"Transporters with Visual Foresight for Solving Unseen Rearrangement Tasks","created":"2022-02-22","cited_by_count":9}],"next_cursor":null}