{"total":210,"rows":[{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388,"area":null},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228,"area":null},{"id":"2403.18105","title":"Large Language Models for Education: A Survey and Outlook","created":"2024-03-26","cited_by_count":188,"area":null},{"id":"2502.00816","title":"Sundial: A Family of Highly Capable Time Series Foundation Models","created":"2025-02-02","cited_by_count":180,"area":null},{"id":"2503.06800","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","created":"2025-03-09","cited_by_count":149,"area":null},{"id":"2502.02492","title":"VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models","created":"2025-02-04","cited_by_count":113,"area":null},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87,"area":null},{"id":"2411.06070","title":"GFT: Graph Foundation Model with Transferable Tree Vocabulary","created":"2024-11-09","cited_by_count":85,"area":null},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77,"area":null},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77,"area":null},{"id":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66,"area":null},{"id":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2503.13265","title":"FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis","created":"2025-03-17","cited_by_count":37,"area":null},{"id":"2410.05227","title":"The Dawn of Video Generation: Preliminary Explorations with SORA-like Models","created":"2024-10-07","cited_by_count":31,"area":null},{"id":"2510.15831","title":"VISTA: A Test-Time Self-Improving Video Generation Agent","created":"2025-10-17","cited_by_count":31,"area":null},{"id":"2406.06087","title":"GAIA: Rethinking Action Quality Assessment for AI-Generated Videos","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2409.07486","title":"MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model","created":"2024-09-04","cited_by_count":28,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"area":null},{"id":"2510.01174","title":"Code2Video: A Code-centric Paradigm for Educational Video Generation","created":"2025-10-01","cited_by_count":27,"area":null},{"id":"2603.12513","title":"MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens","created":"2026-03-12","cited_by_count":27,"area":null},{"id":"2407.21136","title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls","created":"2024-07-30","cited_by_count":26,"area":null},{"id":"2503.08257","title":"DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness","created":"2025-03-11","cited_by_count":26,"area":null},{"id":"2503.20172","title":"Guiding Human-Object Interactions with Rich Geometry and Relations","created":"2025-03-26","cited_by_count":24,"area":null},{"id":"2602.05551","title":"FastVMT: Eliminating Redundancy in Video Motion Transfer","created":"2026-02-05","cited_by_count":23,"area":null},{"id":"2410.05203","title":"Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality","created":"2024-10-07","cited_by_count":22,"area":null},{"id":"2412.16982","title":"InterDance:Reactive 3D Dance Generation with Realistic Duet Interactions","created":"2024-12-22","cited_by_count":22,"area":null},{"id":"2406.14969","title":"Uni-Mol2: Exploring Molecular Pretraining Model at Scale","created":"2024-06-21","cited_by_count":20,"area":null},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19,"area":null},{"id":"2506.10540","title":"AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation","created":"2025-06-12","cited_by_count":19,"area":null},{"id":"2506.07848","title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2506.08003","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","created":"2025-06-09","cited_by_count":15,"area":null},{"id":"2407.08256","title":"Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling","created":"2024-07-11","cited_by_count":13,"area":null},{"id":"2410.05259","title":"GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2506.07865","title":"FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity","created":"2025-06-09","cited_by_count":13,"area":null},{"id":"2410.13287","title":"PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs","created":"2024-10-17","cited_by_count":12,"area":null},{"id":"2411.09547","title":"Piecing It All Together: Verifying Multi-Hop Multimodal Claims","created":"2024-11-14","cited_by_count":12,"area":null},{"id":"2411.11934","title":"SpatialDreamer: Self-supervised Stereo Video Synthesis from Monocular Input","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2412.09597","title":"LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors","created":"2024-12-12","cited_by_count":12,"area":null},{"id":"2501.08295","title":"LayerAnimate: Layer-level Control for Animation","created":"2025-01-14","cited_by_count":12,"area":null},{"id":"2501.13452","title":"EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion","created":"2025-01-23","cited_by_count":12,"area":null},{"id":"2503.06268","title":"Get In Video: Add Anything You Want to the Video","created":"2025-03-08","cited_by_count":12,"area":null},{"id":"2504.02451","title":"ConMo: Controllable Motion Disentanglement and Recomposition for Zero-Shot Motion Transfer","created":"2025-04-03","cited_by_count":12,"area":null},{"id":"2511.15700","title":"First Frame Is the Place to Go for Video Content Customization","created":"2025-11-19","cited_by_count":12,"area":null},{"id":"2408.00777","title":"CATD: Unified Representation Learning for EEG-to-fMRI Cross-Modal Generation","created":"2024-07-16","cited_by_count":11,"area":null},{"id":"2409.09825","title":"GP-GPT: Large Language Model for Gene-Phenotype Mapping","created":"2024-09-15","cited_by_count":11,"area":null},{"id":"2504.11092","title":"Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting","created":"2025-04-15","cited_by_count":11,"area":null},{"id":"2510.16548","title":"NeurIPT: Foundation Model for Neural Interfaces","created":"2025-10-18","cited_by_count":11,"area":null},{"id":"2502.05503","title":"A Physical Coherence Benchmark for Evaluating Video Generation Models via Optical Flow-guided Frame Prediction","created":"2025-02-08","cited_by_count":10,"area":null},{"id":"2601.04151","title":"Apollo: Unified Multi-Task Audio-Video Joint Generation","created":"2026-01-07","cited_by_count":10,"area":null},{"id":"2408.12601","title":"DreamCinema: Cinematic Transfer with Free Camera and 3D Character","created":"2024-08-22","cited_by_count":9,"area":null},{"id":"2411.05027","title":"Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey","created":"2024-11-05","cited_by_count":9,"area":null},{"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,"area":null},{"id":"2405.13902","title":"LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2412.00730","title":"SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2501.01987","title":"Gender Bias in Text-to-Video Generation Models: A case study of Sora","created":"2024-12-30","cited_by_count":8,"area":null},{"id":"2405.02801","title":"Mozart's Touch: A Lightweight Multi-modal Music Generation Framework Based on Pre-Trained Large Models","created":"2024-05-05","cited_by_count":7,"area":null},{"id":"2412.18688","title":"Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2412.20677","title":"Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2502.05539","title":"SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation","created":"2025-02-08","cited_by_count":7,"area":null},{"id":"2506.00433","title":"Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2406.16038","title":"LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control","created":"2024-06-23","cited_by_count":6,"area":null},{"id":"2407.20592","title":"EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos","created":"2024-07-30","cited_by_count":6,"area":null},{"id":"2503.06467","title":"SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts","created":"2025-03-09","cited_by_count":6,"area":null},{"id":"2510.02311","title":"Inferring Dynamic Physical Properties from Video Foundation Models","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2412.07696","title":"SimVS: Simulating World Inconsistencies for Robust View Synthesis","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2412.20601","title":"MATEY: multiscale adaptive foundation models for spatiotemporal physical systems","created":"2024-12-29","cited_by_count":5,"area":null},{"id":"2502.14344","title":"Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism","created":"2025-02-20","cited_by_count":5,"area":null},{"id":"2503.06508","title":"LightMotion: A Light and Tuning-free Method for Simulating Camera Motion in Video Generation","created":"2025-03-09","cited_by_count":5,"area":null},{"id":"2503.23536","title":"A Survey on Unlearnable Data","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2505.10049","title":"Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Field","created":"2025-05-15","cited_by_count":5,"area":null},{"id":"2505.24862","title":"ViStoryBench: Comprehensive Benchmark Suite for Story Visualization","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2509.02466","title":"TeRA: Rethinking Text-guided Realistic 3D Avatar Generation","created":"2025-09-02","cited_by_count":5,"area":null},{"id":"2511.12930","title":"Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration","created":"2025-11-17","cited_by_count":5,"area":null},{"id":"2511.19474","title":"Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks","created":"2025-11-22","cited_by_count":5,"area":null},{"id":"2512.13465","title":"PoseAnything: Universal Pose-guided Video Generation with Part-aware Temporal Coherence","created":"2025-12-15","cited_by_count":5,"area":null},{"id":"2601.00943","title":"PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education","created":"2026-01-02","cited_by_count":5,"area":null},{"id":"2602.03028","title":"MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2606.20799","title":"GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling","created":"2026-06-18","cited_by_count":5,"area":null},{"id":"2408.10437","title":"Understanding Generative AI Content with Embedding Models","created":"2024-08-19","cited_by_count":4,"area":null},{"id":"2508.19445","title":"On Surjectivity of Neural Networks: Can you elicit any behavior from your model?","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2512.09646","title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2512.19817","title":"Generating the Past, Present and Future from a Motion-Blurred Image","created":"2025-12-22","cited_by_count":4,"area":null},{"id":"2602.19285","title":"MRI Contrast Enhancement Kinetics World Model","created":"2026-02-22","cited_by_count":4,"area":null},{"id":"2604.10837","title":"Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation","created":"2026-04-12","cited_by_count":4,"area":null},{"id":"2605.12038","title":"OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2405.00956","title":"SimEndoGS: Efficient Data-driven Scene Simulation using Robotic Surgery Videos via Physics-embedded 3D Gaussians","created":"2024-05-02","cited_by_count":3,"area":null},{"id":"2406.11859","title":"\"Sora is Incredible and Scary\": Emerging Governance Challenges of Text-to-Video Generative AI Models","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2407.14296","title":"Foundation Models for Autonomous Robots in Unstructured Environments","created":"2024-07-19","cited_by_count":3,"area":null},{"id":"2409.01688","title":"Differentially Private Kernel Density Estimation","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2410.08534","title":"Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2411.13602","title":"Translating Electrocardiograms to Cardiac Magnetic Resonance Imaging Useful for Cardiac Assessment and Disease Screening: A Multi-Center Study","created":"2024-11-19","cited_by_count":3,"area":null},{"id":"2502.06891","title":"ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimization","created":"2025-02-09","cited_by_count":3,"area":null},{"id":"2502.17863","title":"A Survey: Spatiotemporal Consistency in Video Generation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2503.16456","title":"Position: Beyond Assistance -- Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2505.17333","title":"Temporal Differential Fields for 4D Motion Modeling via Image-to-Video Synthesis","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2506.21374","title":"Pay Attention to Small Weights","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2508.06511","title":"DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2508.18118","title":"HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2512.08905","title":"Self-Evolving 3D Scene Generation from a Single Image","created":"2025-12-09","cited_by_count":3,"area":null}],"next_cursor":"100"}