{"list":"other","total":73,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2501.12326","title":"UI-TARS: Pioneering Automated GUI Interaction with Native Agents","created":"2025-01-21","cited_by_count":610},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"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":"2402.10329","title":"Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots","created":"2024-02-15","cited_by_count":394},{"id":"2505.07062","title":"Seed1.5-VL Technical Report","created":"2025-05-11","cited_by_count":373},{"id":"2407.08693","title":"Robotic Control via Embodied Chain-of-Thought Reasoning","created":"2024-07-11","cited_by_count":346},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"2406.10721","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","created":"2024-06-15","cited_by_count":251},{"id":"2502.19417","title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","created":"2025-02-26","cited_by_count":221},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2403.01823","title":"RT-H: Action Hierarchies Using Language","created":"2024-03-04","cited_by_count":210},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"2503.15558","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","created":"2025-03-18","cited_by_count":164},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161},{"id":"2403.12910","title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","created":"2024-03-19","cited_by_count":124},{"id":"2311.00899","title":"RoboVQA: Multimodal Long-Horizon Reasoning for Robotics","created":"2023-11-01","cited_by_count":120},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114},{"id":"2507.15493","title":"GR-3 Technical Report","created":"2025-07-21","cited_by_count":111},{"id":"2406.05756","title":"EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models","created":"2024-06-09","cited_by_count":107},{"id":"2404.05955","title":"VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?","created":"2024-04-09","cited_by_count":100},{"id":"2507.02029","title":"RoboBrain 2.0 Technical Report","created":"2025-07-02","cited_by_count":89},{"id":"2406.18915","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","created":"2024-06-27","cited_by_count":83},{"id":"2410.05273","title":"HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers","created":"2024-09-12","cited_by_count":75},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72},{"id":"2502.13059","title":"SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models","created":"2025-02-18","cited_by_count":66},{"id":"2409.14674","title":"RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning","created":"2024-09-23","cited_by_count":49},{"id":"2410.02193","title":"Guiding Long-Horizon Task and Motion Planning with Vision Language Models","created":"2024-10-03","cited_by_count":47},{"id":"2503.21696","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","created":"2025-03-27","cited_by_count":44},{"id":"2401.04157","title":"RePLan: Robotic Replanning with Perception and Language Models","created":"2024-01-08","cited_by_count":41},{"id":"2404.10220","title":"Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V","created":"2024-04-16","cited_by_count":40},{"id":"2412.04458","title":"Cubify Anything: Scaling Indoor 3D Object Detection","created":"2024-12-05","cited_by_count":39},{"id":"2410.08792","title":"VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model","created":"2024-10-11","cited_by_count":37},{"id":"2410.06237","title":"BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation","created":"2024-10-08","cited_by_count":32},{"id":"2310.17555","title":"Interactive Robot Learning from Verbal Correction","created":"2023-10-26","cited_by_count":29},{"id":"2407.21762","title":"ReplanVLM: Replanning Robotic Tasks with Visual Language Models","created":"2024-07-31","cited_by_count":28},{"id":"2504.19442","title":"Triton-distributed: Programming Overlapping Kernels on Distributed AI Systems with the Triton Compiler","created":"2025-04-28","cited_by_count":25},{"id":"2503.20313","title":"TileLink: Generating Efficient Compute-Communication Overlapping Kernels using Tile-Centric Primitives","created":"2025-03-26","cited_by_count":24},{"id":"2110.09992","title":"ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution","created":"2021-10-19","cited_by_count":14},{"id":"2211.06652","title":"Learning Neuro-symbolic Programs for Language Guided Robot Manipulation","created":"2022-11-12","cited_by_count":10},{"id":"1903.09243","title":"Inferring Compact Representations for Efficient Natural Language Understanding of Robot Instructions","created":"2019-03-21","cited_by_count":9},{"id":"2406.05881","title":"Training Fast Robot Policies with Slow Foundation Models","created":"2024-06-09","cited_by_count":2},{"id":"2411.15033","title":"One to rule them all: natural language to bind communication, perception and action","created":"2024-11-22","cited_by_count":2}],"next_cursor":null}