{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2104.00677","title":"Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis","created":"2021-04-01","cited_by_count":464},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250},{"id":"2410.24207","title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","created":"2024-10-31","cited_by_count":248},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"2305.14078","title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","created":"2023-05-23","cited_by_count":231},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229},{"id":"1811.02790","title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","created":"2018-11-07","cited_by_count":204},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172},{"id":"2506.03141","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval","created":"2025-06-03","cited_by_count":163},{"id":"2309.10062","title":"SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models","created":"2023-09-18","cited_by_count":153},{"id":"2503.01661","title":"MUSt3R: Multi-view Network for Stereo 3D Reconstruction","created":"2025-03-03","cited_by_count":141},{"id":"2312.00206","title":"SparseGS: Sparse View Synthesis using 3D Gaussian Splatting","created":"2023-11-30","cited_by_count":134},{"id":"2309.10150","title":"Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions","created":"2023-09-18","cited_by_count":131},{"id":"2501.08325","title":"GameFactory: Creating New Games with Generative Interactive Videos","created":"2025-01-14","cited_by_count":130},{"id":"2506.04308","title":"RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics","created":"2025-06-04","cited_by_count":127},{"id":"2003.06085","title":"Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations","created":"2020-03-13","cited_by_count":115},{"id":"2403.12482","title":"Embodied LLM Agents Learn to Cooperate in Organized Teams","created":"2024-03-19","cited_by_count":82},{"id":"2411.00081","title":"PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks","created":"2024-10-31","cited_by_count":82},{"id":"2210.05178","title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","created":"2022-10-11","cited_by_count":78},{"id":"2312.04565","title":"MuRF: Multi-Baseline Radiance Fields","created":"2023-12-07","cited_by_count":71},{"id":"2409.02920","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)","created":"2024-09-04","cited_by_count":69},{"id":"2312.07472","title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","created":"2023-12-12","cited_by_count":67},{"id":"2305.16309","title":"Imitating Task and Motion Planning with Visuomotor Transformers","created":"2023-05-25","cited_by_count":66},{"id":"2412.04455","title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection","created":"2024-12-05","cited_by_count":63},{"id":"2403.12037","title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","created":"2024-03-18","cited_by_count":53},{"id":"2404.10775","title":"COMBO: Compositional World Models for Embodied Multi-Agent Cooperation","created":"2024-04-16","cited_by_count":49},{"id":"2310.13255","title":"Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds","created":"2023-10-20","cited_by_count":45},{"id":"2407.12998","title":"Surgical Robot Transformer (SRT): Imitation Learning for Surgical Tasks","created":"2024-07-17","cited_by_count":40},{"id":"2309.05655","title":"Dynamic Handover: Throw and Catch with Bimanual Hands","created":"2023-09-11","cited_by_count":35},{"id":"2501.04628","title":"FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency","created":"2025-01-08","cited_by_count":31},{"id":"2503.02390","title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","created":"2025-03-04","cited_by_count":31},{"id":"2503.16408","title":"RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints","created":"2025-03-20","cited_by_count":31},{"id":"2210.08936","title":"S$^3$-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint","created":"2022-10-17","cited_by_count":30},{"id":"2401.17698","title":"Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformer","created":"2024-01-31","cited_by_count":27},{"id":"2410.21040","title":"LiP-LLM: Integrating Linear Programming and dependency graph with Large Language Models for multi-robot task planning","created":"2024-10-28","cited_by_count":24},{"id":"2503.04314","title":"S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting","created":"2025-03-06","cited_by_count":24},{"id":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23},{"id":"2405.18860","title":"Empowering Embodied Manipulation: A Bimanual-Mobile Robot Manipulation Dataset for Household Tasks","created":"2024-05-29","cited_by_count":19},{"id":"2411.09022","title":"DART-LLM: Dependency-Aware Multi-Robot Task Decomposition and Execution using Large Language Models","created":"2024-11-13","cited_by_count":19},{"id":"2503.13217","title":"Dense Policy: Bidirectional Autoregressive Learning of Actions","created":"2025-03-17","cited_by_count":19},{"id":"2503.13861","title":"RAD: Retrieval-Augmented Decision-Making of Meta-Actions with Vision-Language Models in Autonomous Driving","created":"2025-03-18","cited_by_count":18},{"id":"2506.09049","title":"VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning","created":"2025-06-10","cited_by_count":18},{"id":"2406.09738","title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","created":"2024-06-14","cited_by_count":15},{"id":"2505.22634","title":"LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents","created":"2025-05-28","cited_by_count":15},{"id":"2410.24152","title":"Language-Driven Policy Distillation for Cooperative Driving in Multi-Agent Reinforcement Learning","created":"2024-10-31","cited_by_count":14},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13},{"id":"2503.09186","title":"Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework","created":"2025-03-12","cited_by_count":12},{"id":"2502.13894","title":"NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants","created":"2025-02-19","cited_by_count":11},{"id":"2412.03570","title":"Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis","created":"2024-12-04","cited_by_count":9},{"id":"2503.09758","title":"Multi-Agent LLM Actor-Critic Framework for Social Robot Navigation","created":"2025-03-12","cited_by_count":8}],"next_cursor":null}