{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2211.05105","title":"Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models","created":"2022-11-09","cited_by_count":513},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2311.06214","title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","created":"2023-11-10","cited_by_count":378},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","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":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"2303.11408","title":"Stable Bias: Analyzing Societal Representations in Diffusion Models","created":"2023-03-20","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":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177},{"id":"2309.01918","title":"RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking","created":"2023-09-05","cited_by_count":169},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2307.14535","title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","created":"2023-07-26","cited_by_count":159},{"id":"2311.01977","title":"RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches","created":"2023-11-03","cited_by_count":133},{"id":"2402.08191","title":"THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation","created":"2024-02-13","cited_by_count":133},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"2302.06671","title":"GenAug: Retargeting behaviors to unseen situations via Generative Augmentation","created":"2023-02-13","cited_by_count":104},{"id":"2308.16891","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","created":"2023-08-31","cited_by_count":99},{"id":"2309.08587","title":"Compositional Foundation Models for Hierarchical Planning","created":"2023-09-15","cited_by_count":95},{"id":"2209.04899","title":"Instruction-driven history-aware policies for robotic manipulations","created":"2022-09-11","cited_by_count":94},{"id":"2308.15975","title":"RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation","created":"2023-08-30","cited_by_count":90},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75},{"id":"1707.02267","title":"Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task","created":"2017-07-07","cited_by_count":66},{"id":"2312.12491","title":"StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation","created":"2023-12-19","cited_by_count":58},{"id":"1911.09231","title":"Camera-to-Robot Pose Estimation from a Single Image","created":"2019-11-21","cited_by_count":48},{"id":"1906.11176","title":"PyRep: Bringing V-REP to Deep Robot Learning","created":"2019-06-26","cited_by_count":44},{"id":"2403.02709","title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","created":"2024-03-05","cited_by_count":41},{"id":"2402.17768","title":"Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning","created":"2024-02-27","cited_by_count":35},{"id":"2402.10837","title":"Pedipulate: Enabling Manipulation Skills using a Quadruped Robot's Leg","created":"2024-02-16","cited_by_count":27},{"id":"2403.04115","title":"DNAct: Diffusion Guided Multi-Task 3D Policy Learning","created":"2024-03-07","cited_by_count":23},{"id":"1609.03759","title":"3D Simulation for Robot Arm Control with Deep Q-Learning","created":"2016-09-13","cited_by_count":21},{"id":"2405.18196","title":"Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning","created":"2024-05-28","cited_by_count":20},{"id":"2310.13914","title":"Cold Diffusion on the Replay Buffer: Learning to Plan from Known Good States","created":"2023-10-21","cited_by_count":10},{"id":"2312.01097","title":"Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty","created":"2023-12-02","cited_by_count":9},{"id":"2403.11459","title":"ALDM-Grasping: Diffusion-aided Zero-Shot Sim-to-Real Transfer for Robot Grasping","created":"2024-03-18","cited_by_count":7},{"id":"2404.12539","title":"Enabling Stateful Behaviors for Diffusion-based Policy Learning","created":"2024-04-18","cited_by_count":3}],"next_cursor":null}