{"total":135,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429,"area":null},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2601.20540","title":"Advancing Open-source World Models","created":"2026-01-28","cited_by_count":154,"area":"wm"},{"id":"2510.26583","title":"Emu3.5: Native Multimodal Models are World Learners","created":"2025-10-30","cited_by_count":132,"area":"wm"},{"id":"2503.05638","title":"TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models","created":"2025-03-07","cited_by_count":125,"area":"diffusion"},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98,"area":"diffusion"},{"id":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90,"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":"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":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2505.20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","created":"2025-05-26","cited_by_count":73,"area":null},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69,"area":null},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66,"area":null},{"id":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61,"area":null},{"id":"2502.10059","title":"RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control","created":"2025-02-14","cited_by_count":57,"area":null},{"id":"2506.13691","title":"UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions","created":"2025-06-16","cited_by_count":57,"area":null},{"id":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"area":null},{"id":"2509.08519","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","created":"2025-09-10","cited_by_count":47,"area":null},{"id":"2506.03140","title":"CamCloneMaster: Enabling Reference-based Camera Control for Video Generation","created":"2025-06-03","cited_by_count":46,"area":null},{"id":"2509.22799","title":"VideoScore2: Think before You Score in Generative Video Evaluation","created":"2025-09-26","cited_by_count":40,"area":null},{"id":"2506.23858","title":"VMoBA: Mixture-of-Block Attention for Video Diffusion Models","created":"2025-06-30","cited_by_count":37,"area":"diffusion"},{"id":"2510.08485","title":"InstructX: Towards Unified Visual Editing with MLLM Guidance","created":"2025-10-09","cited_by_count":32,"area":"mllm"},{"id":"2506.15838","title":"EchoShot: Multi-Shot Portrait Video Generation","created":"2025-06-16","cited_by_count":29,"area":"diffusion"},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2510.11647","title":"IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment","created":"2025-10-13","cited_by_count":28,"area":null},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26,"area":"moe"},{"id":"2512.21334","title":"Streaming Video Instruction Tuning","created":"2025-12-24","cited_by_count":26,"area":null},{"id":"2503.14935","title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","created":"2025-03-19","cited_by_count":24,"area":"mllm"},{"id":"2502.12782","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","created":"2025-02-18","cited_by_count":23,"area":null},{"id":"2504.10825","title":"OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding","created":"2025-04-15","cited_by_count":22,"area":"diffusion"},{"id":"2510.26794","title":"The Quest for Generalizable Motion Generation: Data, Model, and Evaluation","created":"2025-10-30","cited_by_count":22,"area":"diffusion"},{"id":"2503.01739","title":"VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2503.13319","title":"MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis","created":"2025-03-17","cited_by_count":19,"area":"diffusion"},{"id":"2506.01801","title":"OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation","created":"2025-06-02","cited_by_count":19,"area":"diffusion"},{"id":"2506.04213","title":"FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers","created":"2025-06-04","cited_by_count":18,"area":"diffusion"},{"id":"2506.18851","title":"Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset","created":"2025-06-23","cited_by_count":17,"area":null},{"id":"2507.00162","title":"FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion","created":"2025-06-30","cited_by_count":17,"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":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2504.15681","title":"Vidi: Large Multimodal Models for Video Understanding and Editing","created":"2025-04-22","cited_by_count":15,"area":"mllm"},{"id":"2504.08212","title":"RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements","created":"2025-04-11","cited_by_count":14,"area":null},{"id":"2506.09079","title":"VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks","created":"2025-06-10","cited_by_count":14,"area":"mllm"},{"id":"2601.02204","title":"NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation","created":"2026-01-05","cited_by_count":14,"area":null},{"id":"2604.20796","title":"LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model","created":"2026-04-22","cited_by_count":13,"area":"diffusion"},{"id":"2510.24717","title":"Uniform Discrete Diffusion with Metric Path for Video Generation","created":"2025-10-28","cited_by_count":12,"area":"diffusion"},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2602.21818","title":"SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2502.03207","title":"MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2510.09987","title":"Generative Latent Video Compression","created":"2025-10-11","cited_by_count":11,"area":null},{"id":"2503.24379","title":"Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation","created":"2025-03-31","cited_by_count":10,"area":null},{"id":"2511.23428","title":"DisMo: Disentangled Motion Representations for Open-World Motion Transfer","created":"2025-11-28","cited_by_count":10,"area":null},{"id":"2509.17627","title":"OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models","created":"2025-09-22","cited_by_count":9,"area":"diffusion"},{"id":"2511.16669","title":"Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO","created":"2025-11-20","cited_by_count":9,"area":"lr"},{"id":"2512.06905","title":"Scaling Zero-Shot Reference-to-Video Generation","created":"2025-12-07","cited_by_count":9,"area":null},{"id":"2505.12489","title":"Video-GPT via Next Clip Diffusion","created":"2025-05-18","cited_by_count":8,"area":"wm"},{"id":"2508.21019","title":"Phased One-Step Adversarial Equilibrium for Video Diffusion Models","created":"2025-08-28","cited_by_count":8,"area":"diffusion"},{"id":"2510.12089","title":"Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback","created":"2025-10-14","cited_by_count":8,"area":"diffusion"},{"id":"2602.09609","title":"Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing","created":"2026-02-10","cited_by_count":8,"area":"diffusion"},{"id":"2602.10113","title":"ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2603.19228","title":"SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing","created":"2026-03-19","cited_by_count":8,"area":null},{"id":"2505.15800","title":"Interspatial Attention for Efficient 4D Human Video Generation","created":"2025-05-21","cited_by_count":7,"area":"diffusion"},{"id":"2512.07831","title":"UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation","created":"2025-12-08","cited_by_count":7,"area":null},{"id":"2601.16515","title":"SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer","created":"2026-01-23","cited_by_count":7,"area":"diffusion"},{"id":"2603.06569","title":"Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders","created":"2026-03-06","cited_by_count":7,"area":"mllm"},{"id":"2605.18733","title":"Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory","created":"2026-05-18","cited_by_count":7,"area":null},{"id":"2503.06053","title":"DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2505.19901","title":"Dynamic-I2V: Exploring Image-to-Video Generation Models via Multimodal LLM","created":"2025-05-26","cited_by_count":6,"area":"mllm"},{"id":"2507.04909","title":"HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding","created":"2025-07-07","cited_by_count":6,"area":"mllm"},{"id":"2507.07202","title":"A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality","created":"2025-07-09","cited_by_count":6,"area":null},{"id":"2509.26165","title":"Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models","created":"2025-09-30","cited_by_count":6,"area":"mllm"},{"id":"2511.21129","title":"CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion","created":"2025-11-26","cited_by_count":6,"area":"diffusion"},{"id":"2601.10632","title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","created":"2026-01-15","cited_by_count":6,"area":null},{"id":"2606.06042","title":"LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2606.09639","title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","created":"2026-06-08","cited_by_count":6,"area":null},{"id":"2606.30599","title":"Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2510.08555","title":"VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning","created":"2025-10-09","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":"2601.01720","title":"FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing","created":"2026-01-05","cited_by_count":5,"area":null},{"id":"2603.01685","title":"FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2604.24762","title":"OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer","created":"2026-04-27","cited_by_count":5,"area":null},{"id":"2507.01938","title":"CI-VID: A Coherent Interleaved Text-Video Dataset","created":"2025-07-02","cited_by_count":4,"area":null},{"id":"2510.14977","title":"Terra: Explorable Native 3D World Model with Point Latents","created":"2025-10-16","cited_by_count":4,"area":"wm"},{"id":"2510.18262","title":"UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding","created":"2025-10-21","cited_by_count":4,"area":"mllm"},{"id":"2601.04068","title":"Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models","created":"2026-01-07","cited_by_count":4,"area":"diffusion"},{"id":"2512.05103","title":"TV2TV: A Unified Framework for Interleaved Language and Video Generation","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2603.25527","title":"Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2604.02817","title":"MMPhysVideo: Physically Plausible Video Generation Through Joint RGB-Perception Modeling","created":"2026-04-03","cited_by_count":3,"area":"diffusion"},{"id":"2608.01113","title":"CoT-Edit: Let CoT Guide Instruction Video Editing","created":"2026-08-02","cited_by_count":3,"area":null},{"id":"2608.03046","title":"CAPE-T2V: Captioner-Anchored Prompt Enhancement toward Two-Sided Conditioning Alignment in Text-to-Video Generation","created":"2026-08-04","cited_by_count":3,"area":"diffusion"},{"id":"2502.20811","title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models","created":"2025-02-28","cited_by_count":2,"area":"mllm"},{"id":"2507.13345","title":"Imbalance in Balance: Online Concept Balancing in Generation Models","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2509.11589","title":"MVQA-68K: A Multi-dimensional and Causally-annotated Dataset with Quality Interpretability for Video Assessment","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2512.15560","title":"GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models","created":"2025-12-17","cited_by_count":2,"area":"diffusion"},{"id":"2603.06688","title":"Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2605.12179","title":"SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning","created":"2026-05-12","cited_by_count":2,"area":"alignment"},{"id":"2606.03168","title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.09770","title":"Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2606.20774","title":"TriMotion: Modality-Agnostic Camera Control for Video Generation","created":"2026-06-18","cited_by_count":2,"area":null}],"next_cursor":"100"}