{"total":342,"rows":[{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869,"area":null},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332,"area":null},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580,"area":null},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548,"area":null},{"id":"2302.10174","title":"Towards Universal Fake Image Detectors that Generalize Across Generative Models","created":"2023-02-20","cited_by_count":490,"area":null},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347,"area":null},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345,"area":null},{"id":"2312.04461","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","created":"2023-12-07","cited_by_count":328,"area":null},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313,"area":null},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260,"area":null},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238,"area":null},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"id":"2406.07209","title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","created":"2024-06-11","cited_by_count":144,"area":null},{"id":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141,"area":null},{"id":"2307.08041","title":"Planting a SEED of Vision in Large Language Model","created":"2023-07-16","cited_by_count":140,"area":null},{"id":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136,"area":null},{"id":"2306.00943","title":"Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance","created":"2023-06-01","cited_by_count":129,"area":null},{"id":"2402.05408","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","created":"2024-02-08","cited_by_count":124,"area":null},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107,"area":null},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106,"area":null},{"id":"2406.05338","title":"MotionClone: Training-Free Motion Cloning for Controllable Video Generation","created":"2024-06-08","cited_by_count":105,"area":null},{"id":"2308.01661","title":"BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout","created":"2023-08-03","cited_by_count":102,"area":null},{"id":"2404.18929","title":"DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing","created":"2024-04-29","cited_by_count":94,"area":null},{"id":"2312.02934","title":"WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation","created":"2023-12-05","cited_by_count":93,"area":null},{"id":"2406.17758","title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","created":"2024-06-25","cited_by_count":93,"area":null},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89,"area":null},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75,"area":null},{"id":"2305.18247","title":"TaleCrafter: Interactive Story Visualization with Multiple Characters","created":"2023-05-29","cited_by_count":73,"area":null},{"id":"2412.07759","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation","created":"2024-12-10","cited_by_count":71,"area":null},{"id":"2303.02760","title":"Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes","created":"2023-03-05","cited_by_count":68,"area":null},{"id":"2411.04989","title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","created":"2024-11-07","cited_by_count":68,"area":null},{"id":"2310.18308","title":"Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models","created":"2023-10-27","cited_by_count":64,"area":null},{"id":"2403.10701","title":"IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation","created":"2024-03-15","cited_by_count":64,"area":null},{"id":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61,"area":null},{"id":"2308.00906","title":"ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation","created":"2023-08-02","cited_by_count":59,"area":null},{"id":"2312.05208","title":"ControlRoom3D: Room Generation using Semantic Proxy Rooms","created":"2023-12-08","cited_by_count":56,"area":null},{"id":"2402.13251","title":"FlashTex: Fast Relightable Mesh Texturing with LightControlNet","created":"2024-02-20","cited_by_count":56,"area":null},{"id":"2305.15328","title":"Visual Programming for Text-to-Image Generation and Evaluation","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2404.05014","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","created":"2024-04-07","cited_by_count":51,"area":null},{"id":"2305.14330","title":"DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation","created":"2023-05-23","cited_by_count":49,"area":null},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2305.18286","title":"Photoswap: Personalized Subject Swapping in Images","created":"2023-05-29","cited_by_count":47,"area":null},{"id":"2311.00571","title":"LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing","created":"2023-11-01","cited_by_count":47,"area":null},{"id":"2504.06632","title":"PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering","created":"2025-04-09","cited_by_count":46,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2403.00436","title":"Abductive Ego-View Accident Video Understanding for Safe Driving Perception","created":"2024-03-01","cited_by_count":43,"area":null},{"id":"2410.13830","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","created":"2024-10-17","cited_by_count":43,"area":null},{"id":"2410.09049","title":"SceneCraft: Layout-Guided 3D Scene Generation","created":"2024-10-11","cited_by_count":41,"area":null},{"id":"2412.05263","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","created":"2024-12-06","cited_by_count":40,"area":null},{"id":"2501.04699","title":"EditAR: Unified Conditional Generation with Autoregressive Models","created":"2025-01-08","cited_by_count":40,"area":null},{"id":"2403.00483","title":"RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization","created":"2024-03-01","cited_by_count":39,"area":null},{"id":"2310.08541","title":"Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation","created":"2023-10-12","cited_by_count":38,"area":null},{"id":"2311.11243","title":"AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort","created":"2023-11-19","cited_by_count":38,"area":null},{"id":"2306.12624","title":"DreamEdit: Subject-driven Image Editing","created":"2023-06-22","cited_by_count":37,"area":null},{"id":"2312.09246","title":"SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds","created":"2023-12-14","cited_by_count":37,"area":null},{"id":"2410.12669","title":"3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation","created":"2024-10-16","cited_by_count":37,"area":null},{"id":"2411.06558","title":"Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement","created":"2024-11-10","cited_by_count":37,"area":null},{"id":"2502.18364","title":"ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation","created":"2025-02-25","cited_by_count":37,"area":null},{"id":"2405.01536","title":"Customizing Text-to-Image Models with a Single Image Pair","created":"2024-05-02","cited_by_count":36,"area":null},{"id":"2504.13176","title":"IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design","created":"2025-04-17","cited_by_count":36,"area":null},{"id":"2404.00995","title":"PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2407.02329","title":"MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis","created":"2024-07-02","cited_by_count":35,"area":null},{"id":"2411.15497","title":"AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generation","created":"2024-11-23","cited_by_count":35,"area":null},{"id":"2406.09386","title":"SimGen: Simulator-conditioned Driving Scene Generation","created":"2024-06-13","cited_by_count":34,"area":null},{"id":"2403.05659","title":"Audio-Synchronized Visual Animation","created":"2024-03-08","cited_by_count":32,"area":null},{"id":"2403.13304","title":"DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception","created":"2024-03-20","cited_by_count":32,"area":null},{"id":"2403.19438","title":"SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control","created":"2024-03-28","cited_by_count":32,"area":null},{"id":"2404.07202","title":"UMBRAE: Unified Multimodal Brain Decoding","created":"2024-04-10","cited_by_count":32,"area":null},{"id":"2509.21278","title":"Does FLUX Already Know How to Perform Physically Plausible Image Composition?","created":"2025-09-25","cited_by_count":32,"area":null},{"id":"2403.18551","title":"Attention Calibration for Disentangled Text-to-Image Personalization","created":"2024-03-27","cited_by_count":31,"area":null},{"id":"2404.01197","title":"Getting it Right: Improving Spatial Consistency in Text-to-Image Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2310.10765","title":"BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys","created":"2023-10-16","cited_by_count":29,"area":null},{"id":"2310.12128","title":"DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning","created":"2023-10-18","cited_by_count":29,"area":null},{"id":"2503.12885","title":"DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models","created":"2025-03-17","cited_by_count":28,"area":null},{"id":"2306.14636","title":"Localized Text-to-Image Generation for Free via Cross Attention Control","created":"2023-06-26","cited_by_count":27,"area":null},{"id":"2307.14331","title":"Visual Instruction Inversion: Image Editing via Visual Prompting","created":"2023-07-26","cited_by_count":26,"area":null},{"id":"2310.10644","title":"TOSS:High-quality Text-guided Novel View Synthesis from a Single Image","created":"2023-10-16","cited_by_count":26,"area":null},{"id":"2412.02168","title":"Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis","created":"2024-12-03","cited_by_count":26,"area":null},{"id":"2506.16960","title":"Visual-Instructed Degradation Diffusion for All-in-One Image Restoration","created":"2025-06-20","cited_by_count":26,"area":null},{"id":"2503.23461","title":"Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generation","created":"2025-03-30","cited_by_count":25,"area":null},{"id":"2311.15841","title":"Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation","created":"2023-11-27","cited_by_count":24,"area":null},{"id":"2401.13307","title":"ChatterBox: Multi-round Multimodal Referring and Grounding","created":"2024-01-24","cited_by_count":24,"area":null},{"id":"2404.06425","title":"ZeST: Zero-Shot Material Transfer from a Single Image","created":"2024-04-09","cited_by_count":24,"area":null},{"id":"2404.08639","title":"COCONut: Modernizing COCO Segmentation","created":"2024-04-12","cited_by_count":24,"area":null},{"id":"2406.05871","title":"OmniControlNet: Dual-stage Integration for Conditional Image Generation","created":"2024-06-09","cited_by_count":24,"area":null},{"id":"2304.14630","title":"Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model","created":"2023-04-28","cited_by_count":21,"area":null},{"id":"2312.03584","title":"Context Diffusion: In-Context Aware Image Generation","created":"2023-12-06","cited_by_count":21,"area":null},{"id":"2410.15391","title":"Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint","created":"2024-10-20","cited_by_count":21,"area":null},{"id":"2312.02253","title":"Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2403.01901","title":"FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio","created":"2024-03-04","cited_by_count":20,"area":null},{"id":"2403.05053","title":"PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering","created":"2024-03-08","cited_by_count":20,"area":null},{"id":"2406.01388","title":"AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2503.20672","title":"BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation","created":"2025-03-26","cited_by_count":20,"area":null},{"id":"2403.09093","title":"Desigen: A Pipeline for Controllable Design Template Generation","created":"2024-03-14","cited_by_count":19,"area":null},{"id":"2502.20625","title":"T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting","created":"2025-02-28","cited_by_count":19,"area":null},{"id":"2311.03355","title":"SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis","created":"2023-11-06","cited_by_count":18,"area":null},{"id":"2312.02919","title":"Fine-grained Controllable Video Generation via Object Appearance and Context","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2411.16752","title":"Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy","created":"2024-11-24","cited_by_count":18,"area":null},{"id":"2305.15808","title":"Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback","created":"2023-05-25","cited_by_count":17,"area":null}],"next_cursor":"100"}