{"list":"other","total":102,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"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":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"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":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2506.21539","title":"WorldVLA: Towards Autoregressive Action World Model","created":"2025-06-26","cited_by_count":367},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","created":"2024-03-14","cited_by_count":328},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258},{"id":"2506.15564","title":"Show-o2: Improved Native Unified Multimodal Models","created":"2025-06-18","cited_by_count":250},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2404.12377","title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","created":"2024-04-18","cited_by_count":195},{"id":"2505.23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","created":"2025-05-29","cited_by_count":183},{"id":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138},{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114},{"id":"2503.18938","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","created":"2025-03-24","cited_by_count":114},{"id":"2412.18607","title":"DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers","created":"2024-12-24","cited_by_count":96},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94},{"id":"2510.08531","title":"SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models","created":"2025-10-09","cited_by_count":90},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86},{"id":"2308.07498","title":"DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation","created":"2023-08-14","cited_by_count":85},{"id":"2409.03272","title":"OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving","created":"2024-09-05","cited_by_count":83},{"id":"2412.11198","title":"GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control","created":"2024-12-15","cited_by_count":78},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77},{"id":"2411.17735","title":"3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning","created":"2024-11-23","cited_by_count":75},{"id":"2401.06578","title":"360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model","created":"2024-01-12","cited_by_count":58},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51},{"id":"2507.04047","title":"Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation","created":"2025-07-05","cited_by_count":51},{"id":"2407.01525","title":"ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities","created":"2024-07-01","cited_by_count":47},{"id":"2509.08519","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","created":"2025-09-10","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":"2503.02247","title":"WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation","created":"2025-03-04","cited_by_count":43},{"id":"2410.11989","title":"Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation","created":"2024-10-15","cited_by_count":39},{"id":"2509.10884","title":"Nav-R1: Reasoning and Navigation in Embodied Scenes","created":"2025-09-13","cited_by_count":38},{"id":"2511.11007","title":"VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models","created":"2025-11-14","cited_by_count":37},{"id":"2404.00989","title":"360+x: A Panoptic Multi-modal Scene Understanding Dataset","created":"2024-04-01","cited_by_count":35},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33},{"id":"2509.13317","title":"3D Aware Region Prompted Vision Language Model","created":"2025-09-16","cited_by_count":33},{"id":"2505.05495","title":"Learning 3D Persistent Embodied World Models","created":"2025-05-05","cited_by_count":29},{"id":"2410.03878","title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","created":"2024-10-04","cited_by_count":27},{"id":"2405.09713","title":"SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge","created":"2024-05-15","cited_by_count":25},{"id":"2407.15187","title":"HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions","created":"2024-07-21","cited_by_count":24},{"id":"2412.11100","title":"DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes","created":"2024-12-15","cited_by_count":24},{"id":"2505.22016","title":"PanoWan: Lifting Diffusion Video Generation Models to 360{\\deg} with Latitude/Longitude-aware Mechanisms","created":"2025-05-28","cited_by_count":23},{"id":"2510.18873","title":"DSI-Bench: A Benchmark for Dynamic Spatial Intelligence","created":"2025-10-21","cited_by_count":23},{"id":"2412.05280","title":"Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model","created":"2024-12-06","cited_by_count":18},{"id":"2511.07222","title":"Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images","created":"2025-11-10","cited_by_count":17},{"id":"2501.07819","title":"3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding","created":"2025-01-14","cited_by_count":16},{"id":"2510.21682","title":"WorldGrow: Generating Infinite 3D World","created":"2025-10-24","cited_by_count":16},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15},{"id":"2509.26072","title":"The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge","created":"2025-09-30","cited_by_count":15},{"id":"2511.10017","title":"AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models","created":"2025-11-13","cited_by_count":15},{"id":"2506.17545","title":"Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D Annotations","created":"2025-06-21","cited_by_count":14},{"id":"2307.07757","title":"Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments","created":"2023-07-15","cited_by_count":13},{"id":"2505.14197","title":"Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based Method","created":"2025-05-20","cited_by_count":13},{"id":"2508.13013","title":"EgoTwin: Dreaming Body and View in First Person","created":"2025-08-18","cited_by_count":13},{"id":"2411.11844","title":"Generative World Explorer","created":"2024-11-18","cited_by_count":12},{"id":"2510.11549","title":"ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?","created":"2025-10-13","cited_by_count":12},{"id":"2507.07781","title":"SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes","created":"2025-07-10","cited_by_count":11},{"id":"2504.19500","title":"Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding","created":"2025-04-28","cited_by_count":10},{"id":"2511.06840","title":"PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory","created":"2025-11-10","cited_by_count":9},{"id":"2409.13912","title":"OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping","created":"2024-09-20","cited_by_count":8},{"id":"2508.02512","title":"QuaDreamer: Controllable Panoramic Video Generation for Quadruped Robots","created":"2025-08-04","cited_by_count":8},{"id":"2510.22443","title":"Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents","created":"2025-10-25","cited_by_count":8},{"id":"2411.10945","title":"Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera","created":"2024-11-17","cited_by_count":7},{"id":"2503.09938","title":"PanoGen++: Domain-Adapted Text-Guided Panoramic Environment Generation for Vision-and-Language Navigation","created":"2025-03-13","cited_by_count":6},{"id":"2503.12955","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding","created":"2025-03-17","cited_by_count":6},{"id":"1910.13249","title":"Navigation Agents for the Visually Impaired: A Sidewalk Simulator and Experiments","created":"2019-10-29","cited_by_count":5},{"id":"2509.02164","title":"Omnidirectional Spatial Modeling from Correlated Panoramas","created":"2025-09-02","cited_by_count":5},{"id":"2509.22415","title":"Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models","created":"2025-09-26","cited_by_count":5},{"id":"2510.18054","title":"HouseTour: A Virtual Real Estate A(I)gent","created":"2025-10-20","cited_by_count":5},{"id":"2410.22829","title":"Situational Scene Graph for Structured Human-centric Situation Understanding","created":"2024-10-30","cited_by_count":4},{"id":"2510.11520","title":"mmWalk: Towards Multi-modal Multi-view Walking Assistance","created":"2025-10-13","cited_by_count":3},{"id":"2412.02449","title":"BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understanding","created":"2024-12-03","cited_by_count":2}],"next_cursor":"100"}