{"list":"other","total":77,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2405.14867","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","created":"2024-05-23","cited_by_count":684},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2405.17398","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","created":"2024-05-27","cited_by_count":347},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"2503.01774","title":"Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models","created":"2025-03-03","cited_by_count":161},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67},{"id":"2404.09967","title":"Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model","created":"2024-04-15","cited_by_count":66},{"id":"2407.11633","title":"Scaling Diffusion Transformers to 16 Billion Parameters","created":"2024-07-16","cited_by_count":66},{"id":"2501.18590","title":"DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models","created":"2025-01-30","cited_by_count":57},{"id":"2401.00496","title":"SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge","created":"2023-12-31","cited_by_count":56},{"id":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55},{"id":"2506.09981","title":"ReSim: Reliable World Simulation for Autonomous Driving","created":"2025-06-11","cited_by_count":44},{"id":"2503.15208","title":"DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation","created":"2025-03-19","cited_by_count":40},{"id":"2303.09514","title":"MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation","created":"2023-03-16","cited_by_count":36},{"id":"2408.07981","title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning","created":"2024-08-15","cited_by_count":34},{"id":"2506.02327","title":"Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning","created":"2025-06-02","cited_by_count":34},{"id":"2212.04582","title":"Towards Holistic Surgical Scene Understanding","created":"2022-12-08","cited_by_count":33},{"id":"2510.18313","title":"OmniNWM: Omniscient Driving Navigation World Models","created":"2025-10-21","cited_by_count":33},{"id":"2512.16760","title":"Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future","created":"2025-12-18","cited_by_count":33},{"id":"2412.04842","title":"UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving","created":"2024-12-06","cited_by_count":27},{"id":"2512.10958","title":"WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World","created":"2025-12-11","cited_by_count":23},{"id":"2408.14028","title":"SurGen: Text-Guided Diffusion Model for Surgical Video Generation","created":"2024-08-26","cited_by_count":20},{"id":"2506.03079","title":"ORV: 4D Occupancy-centric Robot Video Generation","created":"2025-06-03","cited_by_count":17},{"id":"2507.12137","title":"AD-GS: Object-Aware B-Spline Gaussian Splatting for Self-Supervised Autonomous Driving","created":"2025-07-16","cited_by_count":17},{"id":"2407.01029","title":"EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splatting","created":"2024-07-01","cited_by_count":16},{"id":"2510.09094","title":"Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation","created":"2025-10-10","cited_by_count":16},{"id":"2407.08944","title":"Bora: Biomedical Generalist Video Generation Model","created":"2024-07-12","cited_by_count":15},{"id":"2412.14018","title":"SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation","created":"2024-12-18","cited_by_count":15},{"id":"2410.09750","title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models","created":"2024-10-13","cited_by_count":13},{"id":"2506.17873","title":"SurgVidLM: Towards Multi-grained Surgical Video Understanding with Large Language Model","created":"2025-06-22","cited_by_count":13},{"id":"2407.20214","title":"SANGRIA: Surgical Video Scene Graph Optimization for Surgical Workflow Prediction","created":"2024-07-29","cited_by_count":12},{"id":"2503.18108","title":"Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving","created":"2025-03-23","cited_by_count":12},{"id":"2412.01717","title":"Driving View Synthesis on Free-form Trajectories with Generative Prior","created":"2024-12-02","cited_by_count":11},{"id":"2505.00704","title":"Controllable Weather Synthesis and Removal with Video Diffusion Models","created":"2025-05-01","cited_by_count":11},{"id":"2506.02265","title":"Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction","created":"2025-06-02","cited_by_count":11},{"id":"2511.01775","title":"How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment","created":"2025-11-03","cited_by_count":11},{"id":"2512.23162","title":"Cosmos-H-Surgical: Learning Surgical Robot Policies from Videos via World Modeling","created":"2025-12-29","cited_by_count":11},{"id":"2412.11183","title":"OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation","created":"2024-12-15","cited_by_count":10},{"id":"2503.02904","title":"Surgical Vision World Model","created":"2025-03-03","cited_by_count":10},{"id":"2505.07449","title":"Ophora: A Large-Scale Data-Driven Text-Guided Ophthalmic Surgical Video Generation Model","created":"2025-05-12","cited_by_count":10},{"id":"2507.05675","title":"MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos","created":"2025-07-08","cited_by_count":9},{"id":"2603.13024","title":"SAW: Toward a Surgical Action World Model via Controllable and Scalable Video Generation","created":"2026-03-13","cited_by_count":9},{"id":"2412.02332","title":"SimuScope: Realistic Endoscopic Synthetic Dataset Generation through Surgical Simulation and Diffusion Models","created":"2024-12-03","cited_by_count":8},{"id":"2506.21287","title":"HieraSurg: Hierarchy-Aware Diffusion Model for Surgical Video Generation","created":"2025-06-26","cited_by_count":8},{"id":"2510.22973","title":"Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method","created":"2025-10-27","cited_by_count":8},{"id":"2602.03242","title":"InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation","created":"2026-02-03","cited_by_count":8},{"id":"2604.21017","title":"Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics","created":"2026-04-22","cited_by_count":8},{"id":"2411.11943","title":"Medical Video Generation for Disease Progression Simulation","created":"2024-11-18","cited_by_count":5},{"id":"2503.12531","title":"Towards Suturing World Models: Learning Predictive Models for Robotic Surgical Tasks","created":"2025-03-16","cited_by_count":5},{"id":"2506.03082","title":"SG2VID: Scene Graphs Enable Fine-Grained Control for Video Synthesis","created":"2025-06-03","cited_by_count":4},{"id":"2506.04956","title":"FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation","created":"2025-06-05","cited_by_count":4},{"id":"2603.12787","title":"Generalized Recognition of Basic Surgical Actions Enables Skill Assessment and Vision-Language-Model-based Surgical Planning","created":"2026-03-13","cited_by_count":3},{"id":"2603.22193","title":"PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation","created":"2026-03-23","cited_by_count":3},{"id":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","cited_by_count":2},{"id":"2504.19918","title":"Enhancing Surgical Documentation through Multimodal Visual-Temporal Transformers and Generative AI","created":"2025-04-28","cited_by_count":2},{"id":"2602.23203","title":"ColoDiff: Integrating Dynamic Consistency With Content Awareness for Colonoscopy Video Generation","created":"2026-02-26","cited_by_count":2},{"id":"2510.07345","title":"Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model","created":"2025-10-07","cited_by_count":1},{"id":"2512.08577","title":"Disturbance-Free Surgical Video Generation from Multi-Camera Shadowless Lamps for Open Surgery","created":"2025-12-09","cited_by_count":1},{"id":"2603.08476","title":"LAR-MoE: Latent-Aligned Routing for Mixture of Experts in Robotic Imitation Learning","created":"2026-03-09","cited_by_count":1},{"id":"2604.00784","title":"An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models","created":"2026-04-01","cited_by_count":1},{"id":"2604.26232","title":"DepthPilot: From Controllability to Interpretability in Colonoscopy Video Generation","created":"2026-04-29","cited_by_count":1}],"next_cursor":null}