{"list":"other","total":83,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2410.07864","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","created":"2024-10-10","cited_by_count":691},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"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":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","created":"2024-03-14","cited_by_count":328},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250},{"id":"2306.14896","title":"RVT: Robotic View Transformer for 3D Object Manipulation","created":"2023-06-26","cited_by_count":225},{"id":"2502.09560","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","created":"2025-02-13","cited_by_count":221},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197},{"id":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175},{"id":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162},{"id":"2301.13670","title":"What Makes Good Examples for Visual In-Context Learning?","created":"2023-01-31","cited_by_count":150},{"id":"2406.08545","title":"RVT-2: Learning Precise Manipulation from Few Demonstrations","created":"2024-06-12","cited_by_count":137},{"id":"2402.08191","title":"THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation","created":"2024-02-13","cited_by_count":133},{"id":"2402.11574","title":"Visual In-Context Learning for Large Vision-Language Models","created":"2024-02-18","cited_by_count":128},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127},{"id":"2502.14420","title":"ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model","created":"2025-02-20","cited_by_count":113},{"id":"2503.07511","title":"PointVLA: Injecting the 3D World into Vision-Language-Action Models","created":"2025-03-10","cited_by_count":105},{"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":"2411.04549","title":"Vision Language Models are In-Context Value Learners","created":"2024-11-07","cited_by_count":90},{"id":"2502.20900","title":"DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping","created":"2025-02-28","cited_by_count":89},{"id":"2406.11815","title":"LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning","created":"2024-06-17","cited_by_count":87},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85},{"id":"2406.18915","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","created":"2024-06-27","cited_by_count":83},{"id":"2403.19578","title":"Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics","created":"2024-03-28","cited_by_count":74},{"id":"2503.19757","title":"Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy","created":"2025-03-25","cited_by_count":74},{"id":"2408.15980","title":"In-Context Imitation Learning via Next-Token Prediction","created":"2024-08-28","cited_by_count":70},{"id":"2206.08522","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","created":"2022-06-17","cited_by_count":68},{"id":"2501.18564","title":"SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation","created":"2025-01-30","cited_by_count":61},{"id":"2402.19432","title":"Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation","created":"2024-02-29","cited_by_count":60},{"id":"2501.03841","title":"OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints","created":"2025-01-07","cited_by_count":59},{"id":"2310.09289","title":"An Unbiased Look at Datasets for Visuo-Motor Pre-Training","created":"2023-10-13","cited_by_count":42},{"id":"2405.19291","title":"Grasp as You Say: Language-guided Dexterous Grasp Generation","created":"2024-05-29","cited_by_count":40},{"id":"2411.12633","title":"Instant Policy: In-Context Imitation Learning via Graph Diffusion","created":"2024-11-19","cited_by_count":39},{"id":"2410.01345","title":"Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy","created":"2024-10-02","cited_by_count":38},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36},{"id":"2503.23751","title":"Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks","created":"2025-03-31","cited_by_count":28},{"id":"2410.12782","title":"In-Context Learning Enables Robot Action Prediction in LLMs","created":"2024-10-16","cited_by_count":27},{"id":"2503.07360","title":"AffordDexGrasp: Open-set Language-guided Dexterous Grasp with Generalizable-Instructive Affordance","created":"2025-03-10","cited_by_count":27},{"id":"2406.14235","title":"Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation","created":"2024-06-20","cited_by_count":23},{"id":"2407.08366","title":"An Economic Framework for 6-DoF Grasp Detection","created":"2024-07-11","cited_by_count":23},{"id":"2308.15989","title":"DiffuVolume: Diffusion Model for Volume based Stereo Matching","created":"2023-08-30","cited_by_count":16},{"id":"2406.09738","title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","created":"2024-06-14","cited_by_count":15},{"id":"2411.12286","title":"GLOVER: Generalizable Open-Vocabulary Affordance Reasoning for Task-Oriented Grasping","created":"2024-11-19","cited_by_count":15},{"id":"2503.09186","title":"Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework","created":"2025-03-12","cited_by_count":12},{"id":"2402.05188","title":"InCoRo: In-Context Learning for Robotics Control with Feedback Loops","created":"2024-02-07","cited_by_count":10},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8},{"id":"2403.16535","title":"Arm-Constrained Curriculum Learning for Loco-Manipulation of the Wheel-Legged Robot","created":"2024-03-25","cited_by_count":8},{"id":"2501.18733","title":"Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation","created":"2025-01-30","cited_by_count":8},{"id":"2409.20154","title":"GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation","created":"2024-09-30","cited_by_count":5}],"next_cursor":null}