{"total":48,"rows":[{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777,"area":null},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752,"area":null},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"area":null},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457,"area":null},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388,"area":null},{"id":"2401.13627","title":"Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild","created":"2024-01-24","cited_by_count":286,"area":null},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159,"area":null},{"id":"2410.13863","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","created":"2024-10-17","cited_by_count":147,"area":null},{"id":"2312.16272","title":"SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation","created":"2023-12-26","cited_by_count":143,"area":null},{"id":"2305.19327","title":"Cones 2: Customizable Image Synthesis with Multiple Subjects","created":"2023-05-30","cited_by_count":101,"area":null},{"id":"2308.09710","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","created":"2023-08-18","cited_by_count":101,"area":null},{"id":"2312.10113","title":"Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation","created":"2023-12-15","cited_by_count":62,"area":null},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58,"area":null},{"id":"2312.02928","title":"LivePhoto: Real Image Animation with Text-guided Motion Control","created":"2023-12-05","cited_by_count":44,"area":null},{"id":"2404.16771","title":"ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving","created":"2024-04-25","cited_by_count":43,"area":null},{"id":"2412.09604","title":"SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding","created":"2024-12-12","cited_by_count":42,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2412.15321","title":"Next Patch Prediction for Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":26,"area":null},{"id":"2404.06451","title":"SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2410.18978","title":"Framer: Interactive Frame Interpolation","created":"2024-10-24","cited_by_count":24,"area":null},{"id":"2309.03599","title":"Chasing Consistency in Text-to-3D Generation from a Single Image","created":"2023-09-07","cited_by_count":13,"area":null},{"id":"2501.09833","title":"Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts","created":"2025-01-16","cited_by_count":12,"area":null},{"id":"2509.19282","title":"OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps","created":"2025-09-23","cited_by_count":10,"area":null},{"id":"2412.07767","title":"Learning Visual Generative Priors without Text","created":"2024-12-10","cited_by_count":8,"area":null},{"id":"2412.06510","title":"AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesis","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2312.14385","title":"Generative AI Beyond LLMs: System Implications of Multi-Modal Generation","created":"2023-12-22","cited_by_count":6,"area":null},{"id":"2407.20592","title":"EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos","created":"2024-07-30","cited_by_count":6,"area":null},{"id":"2405.06948","title":"Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation","created":"2024-05-11","cited_by_count":5,"area":null},{"id":"2411.04967","title":"AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2405.07913","title":"CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models","created":"2024-05-13","cited_by_count":4,"area":null},{"id":"2502.17793","title":"SYNTHIA: Novel Concept Design with Affordance Composition","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2411.14808","title":"High-Resolution Image Synthesis via Next-Token Prediction","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2501.08727","title":"Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models","created":"2025-01-15","cited_by_count":3,"area":null},{"id":"2511.04520","title":"THEval. Evaluation Framework for Talking Head Video Generation","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2412.06413","title":"World-Consistent Data Generation for Vision-and-Language Navigation","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2508.19791","title":"Color Bind: Exploring Color Perception in Text-to-Image Models","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2405.08114","title":"RATLIP: Generative Adversarial CLIP Text-to-Image Synthesis Based on Recurrent Affine Transformations","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2405.16501","title":"User-Friendly Customized Generation with Multi-Modal Prompts","created":"2024-05-26","cited_by_count":1,"area":null},{"id":"2503.06860","title":"Towards Generalization of Tactile Image Generation: Reference-Free Evaluation in a Leakage-Free Setting","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2509.19731","title":"CAMILA: Context-Aware Masking for Image Editing with Language Alignment","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2602.12100","title":"AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2605.23178","title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.06477","title":"Complexity-Balanced Diffusion Splitting","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.18105","title":"OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2309.17196","title":"ResBit: Residual Bit Vector for Categorical Values","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2510.15194","title":"Salient Concept-Aware Generative Data Augmentation","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.21775","title":"Face-MakeUpV2: Facial Consistency Learning for Controllable Text-to-Image Generation","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2605.17294","title":"HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing","created":"2026-05-17","cited_by_count":0,"area":null}],"next_cursor":null}