{"total":60,"rows":[{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114,"area":"diffusion"},{"id":"2305.13655","title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models","created":"2023-05-23","cited_by_count":243,"area":"diffusion"},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"area":null},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104,"area":null},{"id":"2406.11815","title":"LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning","created":"2024-06-17","cited_by_count":87,"area":"mllm"},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75,"area":"diffusion"},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2111.09297","title":"Learning to Compose Visual Relations","created":"2021-11-17","cited_by_count":72,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2204.03574","title":"Learning to Compose Soft Prompts for Compositional Zero-Shot Learning","created":"2022-04-07","cited_by_count":67,"area":"mllm"},{"id":"2211.11138","title":"Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training","created":"2022-11-21","cited_by_count":56,"area":null},{"id":"2108.01176","title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","created":"2021-08-02","cited_by_count":52,"area":null},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51,"area":null},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43,"area":null},{"id":"2304.14573","title":"SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesis","created":"2023-04-28","cited_by_count":41,"area":"diffusion"},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2202.04178","title":"VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming","created":"2022-02-07","cited_by_count":31,"area":"lr"},{"id":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25,"area":"mllm"},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2103.13722","title":"AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Style","created":"2021-03-25","cited_by_count":11,"area":null},{"id":"2205.02958","title":"Scene Graph Expansion for Semantics-Guided Image Outpainting","created":"2022-05-05","cited_by_count":11,"area":null},{"id":"2410.00447","title":"Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation","created":"2024-10-01","cited_by_count":11,"area":"diffusion"},{"id":"2307.09621","title":"Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration","created":"2023-07-18","cited_by_count":9,"area":null},{"id":"2211.06119","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","created":"2022-11-11","cited_by_count":8,"area":null},{"id":"2303.04634","title":"Transformer-based Image Generation from Scene Graphs","created":"2023-03-08","cited_by_count":8,"area":null},{"id":"2304.07509","title":"Multi-View Graph Representation Learning Beyond Homophily","created":"2023-04-15","cited_by_count":8,"area":null},{"id":"2110.11918","title":"MIGS: Meta Image Generation from Scene Graphs","created":"2021-10-22","cited_by_count":7,"area":null},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2505.01104","title":"VSC: Visual Search Compositional Text-to-Image Diffusion Model","created":"2025-05-02","cited_by_count":7,"area":"diffusion"},{"id":"2403.13589","title":"ReGround: Improving Textual and Spatial Grounding at No Cost","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2510.15963","title":"ESCA: Contextualizing Embodied Agents via Scene-Graph Generation","created":"2025-10-11","cited_by_count":6,"area":"mllm"},{"id":"2304.13722","title":"Controllable Image Generation via Collage Representations","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2407.15502","title":"WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentation","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2304.00590","title":"SPAN: Learning Similarity between Scene Graphs and Images with Transformers","created":"2023-04-02","cited_by_count":3,"area":null},{"id":"2311.02247","title":"PRISM: Progressive Restoration for Scene Graph-based Image Manipulation","created":"2023-11-03","cited_by_count":3,"area":null},{"id":"2509.02295","title":"Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image","created":"2025-09-02","cited_by_count":3,"area":"diffusion"},{"id":"2602.00414","title":"Toward Autonomous Laboratory Safety Monitoring with Vision Language Models: Learning to See Hazards Through Scene Structure","created":"2026-01-31","cited_by_count":3,"area":"mllm"},{"id":"2304.09012","title":"GUILGET: GUI Layout GEneration with Transformer","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2305.03983","title":"Multi-object Video Generation from Single Frame Layouts","created":"2023-05-06","cited_by_count":2,"area":null},{"id":"2307.03538","title":"Language-free Compositional Action Generation via Decoupling Refinement","created":"2023-07-07","cited_by_count":2,"area":null},{"id":"2310.17451","title":"Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings","created":"2023-10-26","cited_by_count":2,"area":"lr"},{"id":"2401.14111","title":"Image Synthesis with Graph Conditioning: CLIP-Guided Diffusion Models for Scene Graphs","created":"2024-01-25","cited_by_count":2,"area":"diffusion"},{"id":"2410.01816","title":"Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospects","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2504.06432","title":"D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition","created":"2025-04-08","cited_by_count":2,"area":"diffusion"},{"id":"2505.07815","title":"Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models","created":"2025-05-12","cited_by_count":2,"area":"mllm"},{"id":"2207.00545","title":"Transforming Image Generation from Scene Graphs","created":"2022-07-01","cited_by_count":1,"area":null},{"id":"2211.14544","title":"Target-Free Text-guided Image Manipulation","created":"2022-11-26","cited_by_count":1,"area":null},{"id":"2602.09165","title":"All-in-One Conditioning for Text-to-Image Synthesis","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2106.09015","title":"Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis","created":"2021-06-16","cited_by_count":0,"area":null},{"id":"2206.06346","title":"Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2309.10430","title":"Predicate Classification Using Optimal Transport Loss in Scene Graph Generation","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2405.03650","title":"Generated Contents Enrichment","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2406.10469","title":"Object-Attribute-Relation Representation Based Video Semantic Communication","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2408.14187","title":"Ensemble Predicate Decoding for Unbiased Scene Graph Generation","created":"2024-08-26","cited_by_count":0,"area":null},{"id":"2412.00067","title":"Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphs","created":"2024-11-25","cited_by_count":0,"area":"safety"},{"id":"2601.21498","title":"SimGraph: A Unified Framework for Scene Graph-Based Image Generation and Editing","created":"2026-01-29","cited_by_count":0,"area":null}],"next_cursor":null}