{"total":61,"rows":[{"id":"2402.17525","title":"Diffusion Model-Based Image Editing: A Survey","created":"2024-02-27","cited_by_count":212,"area":"diffusion"},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174,"area":null},{"id":"2403.01248","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","created":"2024-03-02","cited_by_count":134,"area":"agents"},{"id":"2412.00596","title":"PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation","created":"2024-11-30","cited_by_count":80,"area":"diffusion"},{"id":"2403.05131","title":"Sora as a World Model? A Complete Survey on Text-to-Video Generation","created":"2024-03-08","cited_by_count":53,"area":"wm"},{"id":"2501.02189","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","created":"2025-01-04","cited_by_count":47,"area":"mllm"},{"id":"2509.21309","title":"NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics","created":"2025-09-25","cited_by_count":41,"area":null},{"id":"2506.23135","title":"RoboScape: Physics-informed Embodied World Model","created":"2025-06-29","cited_by_count":40,"area":"wm"},{"id":"2505.00337","title":"T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation","created":"2025-05-01","cited_by_count":39,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2503.21765","title":"Exploring the Evolution of Physics Cognition in Video Generation: A Survey","created":"2025-03-27","cited_by_count":31,"area":"diffusion"},{"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":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2512.00425","title":"What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards","created":"2025-11-29","cited_by_count":25,"area":"diffusion"},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"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":"2406.06465","title":"AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction","created":"2024-06-10","cited_by_count":21,"area":"diffusion"},{"id":"2508.08228","title":"LL3M: Large Language 3D Modelers","created":"2025-08-11","cited_by_count":20,"area":null},{"id":"2510.04401","title":"Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting","created":"2025-10-06","cited_by_count":18,"area":"mllm"},{"id":"2412.03347","title":"DIVE: Taming DINO for Subject-Driven Video Editing","created":"2024-12-04","cited_by_count":17,"area":"diffusion"},{"id":"2601.11087","title":"PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models","created":"2026-01-16","cited_by_count":17,"area":"deeprl"},{"id":"2503.20822","title":"Synthetic Video Enhances Physical Fidelity in Video Synthesis","created":"2025-03-26","cited_by_count":15,"area":null},{"id":"2601.18577","title":"Self-Refining Video Sampling","created":"2026-01-26","cited_by_count":15,"area":null},{"id":"2603.06408","title":"Physical Simulator In-the-Loop Video Generation","created":"2026-03-06","cited_by_count":14,"area":"diffusion"},{"id":"2510.13809","title":"PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning","created":"2025-10-15","cited_by_count":12,"area":"wm"},{"id":"2504.04051","title":"Can You Count to Nine? A Human Evaluation Benchmark for Counting Limits in Modern Text-to-Video Models","created":"2025-04-05","cited_by_count":10,"area":"diffusion"},{"id":"2506.22432","title":"Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxy","created":"2025-06-27","cited_by_count":9,"area":null},{"id":"2412.11152","title":"Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editing","created":"2024-12-15","cited_by_count":8,"area":"diffusion"},{"id":"2411.18807","title":"Reconstructing Animals and the Wild","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2602.13294","title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","created":"2026-02-09","cited_by_count":7,"area":"lr"},{"id":"2412.14484","title":"Llama Learns to Direct: DirectorLLM for Human-Centric Video Generation","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2605.28230","title":"Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation","created":"2026-05-27","cited_by_count":6,"area":null},{"id":"2508.15227","title":"GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design","created":"2025-08-21","cited_by_count":5,"area":null},{"id":"2512.03350","title":"SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2604.22984","title":"BrickNet: Graph-Backed Generative Brick Assembly","created":"2026-04-24","cited_by_count":5,"area":null},{"id":"2607.21522","title":"GS-Agent: Creating 4D Physical Worlds With Generative Simulation","created":"2026-07-23","cited_by_count":5,"area":"agents"},{"id":"2503.19351","title":"Multi-Object Sketch Animation by Scene Decomposition and Motion Planning","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2601.07143","title":"EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent","created":"2026-01-12","cited_by_count":4,"area":"agents"},{"id":"2603.13770","title":"PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment","created":"2026-03-14","cited_by_count":4,"area":"diffusion"},{"id":"2410.24219","title":"Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2510.04978","title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","created":"2025-10-06","cited_by_count":3,"area":"wm"},{"id":"2512.24986","title":"PhysTalk: Language-driven Real-time Physics in 3D Gaussian Scenes","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2603.25931","title":"DiReCT: Disentangled Regularization of Contrastive Trajectories for Physics-Refined Video Generation","created":"2026-03-26","cited_by_count":2,"area":"diffusion"},{"id":"2604.07348","title":"MoRight: Motion Control Done Right","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2604.10383","title":"Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios","created":"2026-04-11","cited_by_count":2,"area":"agents"},{"id":"2609.23658","title":"Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms","created":"2026-09-20","cited_by_count":2,"area":"diffusion"},{"id":"2409.10090","title":"InteractPro: A Unified Framework for Motion-Aware Image Composition","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2503.00276","title":"Learning to Animate Images from A Few Videos to Portray Delicate Human Actions","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2512.17152","title":"PhysFire-WM: A Physics-Informed World Model for Emulating Fire Spread Dynamics","created":"2025-12-19","cited_by_count":1,"area":"wm"},{"id":"2603.15627","title":"Physics-Informed Video Diffusion For Shallow Water Equations","created":"2026-02-24","cited_by_count":1,"area":"diffusion"},{"id":"2603.18639","title":"OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2606.15015","title":"NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2608.24169","title":"ViSculpt: Visual-Centric Agentic Geometry Editing","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2504.02361","title":"MG-Gen: Single Image to Motion Graphics Generation","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2507.01711","title":"Component Adaptive Clustering for Generalized Category Discovery","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2512.22016","title":"SketchPlay: Intuitive Creation of Physically Realistic VR Content with Gesture-Driven Sketching","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2606.27741","title":"SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models","created":"2026-06-26","cited_by_count":0,"area":"diffusion"},{"id":"2608.16513","title":"MLLM-Guided Semantic Correction for Text-to-Video Generation","created":"2026-08-17","cited_by_count":0,"area":"diffusion"},{"id":"2609.08215","title":"PhysFlow: Physics-Aware Optical Flow for Motion Controllable Video Generation","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.15392","title":"ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.02197","title":"HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}