{"list":"other","total":89,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2310.10642","title":"Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting","created":"2023-10-16","cited_by_count":476},{"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":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2411.15738","title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","created":"2024-11-24","cited_by_count":241},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202},{"id":"2508.13009","title":"Matrix-game 2.0: An open-source real-time and streaming interactive world model","created":"2025-08-18","cited_by_count":186},{"id":"2503.20523","title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","created":"2025-03-26","cited_by_count":185},{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175},{"id":"2512.14614","title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","created":"2025-12-16","cited_by_count":170},{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134},{"id":"2412.03558","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","created":"2024-12-04","cited_by_count":117},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111},{"id":"2412.07774","title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics","created":"2024-12-10","cited_by_count":102},{"id":"2506.17201","title":"Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition","created":"2025-06-20","cited_by_count":98},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95},{"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":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88},{"id":"2512.19432","title":"MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments","created":"2025-12-22","cited_by_count":72},{"id":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67},{"id":"2312.16794","title":"ZONE: Zero-Shot Instruction-Guided Local Editing","created":"2023-12-28","cited_by_count":62},{"id":"2511.23429","title":"Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model","created":"2025-11-28","cited_by_count":61},{"id":"2505.14671","title":"UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens","created":"2025-05-20","cited_by_count":56},{"id":"2411.11706","title":"MC-LLaVA: Multi-Concept Personalized Vision-Language Model","created":"2024-11-18","cited_by_count":54},{"id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51},{"id":"2507.05241","title":"SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?","created":"2025-07-07","cited_by_count":47},{"id":"2512.14699","title":"MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives","created":"2025-12-16","cited_by_count":45},{"id":"2510.19430","title":"GigaBrain-0: A World Model-Powered Vision-Language-Action Model","created":"2025-10-22","cited_by_count":44},{"id":"2510.26802","title":"Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark","created":"2025-10-30","cited_by_count":43},{"id":"2509.19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation","created":"2025-09-23","cited_by_count":41},{"id":"2405.14785","title":"EditWorld: Simulating World Dynamics for Instruction-Following Image Editing","created":"2024-05-23","cited_by_count":38},{"id":"2511.15848","title":"Step-Audio-R1 Technical Report","created":"2025-11-19","cited_by_count":36},{"id":"2506.21448","title":"ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing","created":"2025-06-26","cited_by_count":34},{"id":"2512.08931","title":"Astra: General Interactive World Model with Autoregressive Denoising","created":"2025-12-09","cited_by_count":33},{"id":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32},{"id":"2510.13678","title":"FlashWorld: High-quality 3D Scene Generation within Seconds","created":"2025-10-15","cited_by_count":32},{"id":"2407.00114","title":"OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents","created":"2024-06-27","cited_by_count":30},{"id":"2512.18099","title":"SAM Audio: Segment Anything in Audio","created":"2025-12-19","cited_by_count":30},{"id":"2502.10498","title":"The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey","created":"2025-02-14","cited_by_count":29},{"id":"2510.06710","title":"RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models","created":"2025-10-08","cited_by_count":28},{"id":"2502.03814","title":"Large Language Models for Multi-Robot Systems: A Survey","created":"2025-02-06","cited_by_count":27},{"id":"2508.12109","title":"Simple o3: Towards Interleaved Vision-Language Reasoning","created":"2025-08-16","cited_by_count":24},{"id":"2506.07235","title":"Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification","created":"2025-06-08","cited_by_count":21},{"id":"2508.15827","title":"Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models","created":"2025-08-18","cited_by_count":21},{"id":"2509.09595","title":"Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis","created":"2025-09-11","cited_by_count":21},{"id":"2511.08892","title":"Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds","created":"2025-11-12","cited_by_count":21},{"id":"2511.19304","title":"AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning","created":"2025-11-24","cited_by_count":20},{"id":"2410.07155","title":"Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis","created":"2024-10-09","cited_by_count":19},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15},{"id":"2509.01659","title":"Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025","created":"2025-09-01","cited_by_count":14},{"id":"2510.19195","title":"Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks","created":"2025-10-22","cited_by_count":14},{"id":"2510.26796","title":"See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting","created":"2025-10-30","cited_by_count":12},{"id":"2512.11749","title":"SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder","created":"2025-12-12","cited_by_count":12},{"id":"2310.05375","title":"IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts","created":"2023-10-09","cited_by_count":11},{"id":"2503.13435","title":"WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes","created":"2025-03-17","cited_by_count":11},{"id":"2512.10949","title":"Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation","created":"2025-12-11","cited_by_count":10},{"id":"2512.12675","title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","created":"2025-12-14","cited_by_count":10},{"id":"2410.09009","title":"Semantic Score Distillation Sampling for Compositional Text-to-3D Generation","created":"2024-10-11","cited_by_count":9},{"id":"2601.10061","title":"CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation","created":"2026-01-15","cited_by_count":9},{"id":"2509.06079","title":"Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge","created":"2025-09-07","cited_by_count":6}],"next_cursor":null}