{"list":"other","total":53,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2404.07191","title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","created":"2024-04-10","cited_by_count":433},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2502.06608","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","created":"2025-02-10","cited_by_count":213},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2404.13026","title":"PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation","created":"2024-04-19","cited_by_count":191},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"2303.14207","title":"DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis","created":"2023-03-24","cited_by_count":166},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125},{"id":"2506.16504","title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","created":"2025-06-19","cited_by_count":125},{"id":"2402.07207","title":"GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting","created":"2024-02-11","cited_by_count":109},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98},{"id":"2404.06903","title":"DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting","created":"2024-04-10","cited_by_count":82},{"id":"2501.18982","title":"OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation","created":"2025-01-31","cited_by_count":69},{"id":"2503.20746","title":"PhysGen3D: Crafting a Miniature Interactive World from a Single Image","created":"2025-03-26","cited_by_count":66},{"id":"2412.18608","title":"PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models","created":"2024-12-24","cited_by_count":62},{"id":"2405.16888","title":"Part123: Part-aware 3D Reconstruction from a Single-view Image","created":"2024-05-27","cited_by_count":55},{"id":"2503.13439","title":"Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images","created":"2025-03-17","cited_by_count":54},{"id":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54},{"id":"2505.19386","title":"Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals","created":"2025-05-26","cited_by_count":53},{"id":"2503.23368","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","created":"2025-03-30","cited_by_count":52},{"id":"2411.12469","title":"AI Flow at the Network Edge","created":"2024-11-19","cited_by_count":46},{"id":"2505.18151","title":"WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions","created":"2025-05-23","cited_by_count":45},{"id":"2501.16550","title":"PhysAnimator: Physics-Guided Generative Cartoon Animation","created":"2025-01-27","cited_by_count":42},{"id":"2410.09049","title":"SceneCraft: Layout-Guided 3D Scene Generation","created":"2024-10-11","cited_by_count":41},{"id":"2509.20358","title":"PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation","created":"2025-09-24","cited_by_count":41},{"id":"2601.10553","title":"Inference-time Physics Alignment of Video Generative Models with Latent World Models","created":"2026-01-15","cited_by_count":37},{"id":"2312.04424","title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views","created":"2023-12-07","cited_by_count":33},{"id":"2603.05449","title":"RealWonder: Real-Time Physical Action-Conditioned Video Generation","created":"2026-03-05","cited_by_count":22},{"id":"2508.03334","title":"Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation","created":"2025-08-05","cited_by_count":21},{"id":"2511.21978","title":"PAT3D: Physics-Augmented Text-to-3D Scene Generation","created":"2025-11-26","cited_by_count":16},{"id":"2601.00051","title":"TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model","created":"2025-12-31","cited_by_count":16},{"id":"2503.15855","title":"VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling","created":"2025-03-20","cited_by_count":14},{"id":"2501.02519","title":"Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors","created":"2025-01-05","cited_by_count":13},{"id":"2412.09597","title":"LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors","created":"2024-12-12","cited_by_count":12},{"id":"2512.24300","title":"Generative Video Compression: Towards 0.01% Compression Rate for Video Transmission","created":"2025-12-30","cited_by_count":12},{"id":"2411.19492","title":"Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling","created":"2024-11-29","cited_by_count":11},{"id":"2604.03723","title":"SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation","created":"2026-04-04","cited_by_count":10},{"id":"2511.12633","title":"Denoising Vision Transformer Autoencoder with Spectral Self-Regularization","created":"2025-11-16","cited_by_count":7},{"id":"2601.03665","title":"PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance","created":"2026-01-07","cited_by_count":6},{"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},{"id":"2603.06095","title":"Enhancing Neural Video Compression of Static Scenes with Positive-Incentive Noise","created":"2026-03-06","cited_by_count":3},{"id":"2510.25279","title":"Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation","created":"2025-10-29","cited_by_count":2}],"next_cursor":null}