{"total":34,"rows":[{"id":"2309.05922","title":"A Survey of Hallucination in Large Foundation Models","created":"2023-09-12","cited_by_count":368,"area":null},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100,"area":null},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74,"area":null},{"id":"2504.15009","title":"Insert Anything: Image Insertion via In-Context Editing in DiT","created":"2025-04-21","cited_by_count":61,"area":null},{"id":"2312.07322","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2409.04559","title":"Thinking Outside the BBox: Unconstrained Generative Object Compositing","created":"2024-09-06","cited_by_count":19,"area":null},{"id":"2309.15508","title":"DreamCom: Finetuning Text-guided Inpainting Model for Image Composition","created":"2023-09-27","cited_by_count":17,"area":null},{"id":"2408.12093","title":"LLM-enhanced Scene Graph Learning for Household Rearrangement","created":"2024-08-22","cited_by_count":12,"area":null},{"id":"2407.15446","title":"Text2Place: Affordance-aware Text Guided Human Placement","created":"2024-07-22","cited_by_count":11,"area":null},{"id":"2510.03135","title":"Mask2IV: Interaction-Centric Video Generation via Mask Trajectories","created":"2025-10-03","cited_by_count":10,"area":null},{"id":"2502.05165","title":"Multitwine: Multi-Object Compositing with Text and Layout Control","created":"2025-02-07","cited_by_count":9,"area":null},{"id":"2401.10822","title":"ActAnywhere: Subject-Aware Video Background Generation","created":"2024-01-19","cited_by_count":8,"area":null},{"id":"2410.13911","title":"GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2412.13185","title":"Move-in-2D: 2D-Conditioned Human Motion Generation","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2412.14462","title":"Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2312.14579","title":"Synthesizing Environment-Specific People in Photographs","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2504.06801","title":"MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection","created":"2025-04-09","cited_by_count":4,"area":null},{"id":"2506.21272","title":"FairyGen: Storied Cartoon Video from a Single Child-Drawn Character","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2602.13326","title":"MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animation","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2409.14379","title":"GroupDiff: Diffusion-based Group Portrait Editing","created":"2024-09-22","cited_by_count":2,"area":null},{"id":"2409.15846","title":"Potential Field as Scene Affordance for Behavior Change-Based Visual Risk Object Identification","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2506.01004","title":"MoCA-Video: Motion-Aware Concept Alignment for Consistent Video Editing","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2510.03200","title":"MonSTeR: a Unified Model for Motion, Scene, Text Retrieval","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2603.10685","title":"A$^2$-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2507.00334","title":"Populate-A-Scene: Affordance-Aware Human Video Generation","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2604.19673","title":"InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.07402","title":"InsHuman: Towards Natural and Identity-Preserving Human Insertion","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2501.12393","title":"Towards Affordance-Aware Articulation Synthesis for Rigged Objects","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2503.09154","title":"SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.04052","title":"Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2603.08020","title":"VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusion","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2605.06667","title":"ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.09388","title":"Efficient Human-Contact Representation for Human-Scene Interaction","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}