{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"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},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"2401.09603","title":"Rethinking FID: Towards a Better Evaluation Metric for Image Generation","created":"2023-11-30","cited_by_count":310},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2307.10816","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","created":"2023-07-20","cited_by_count":282},{"id":"2303.17189","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","created":"2023-03-30","cited_by_count":259},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254},{"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},{"id":"2501.09732","title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","created":"2025-01-16","cited_by_count":234},{"id":"2401.11708","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","created":"2024-01-22","cited_by_count":224},{"id":"2211.14305","title":"SpaText: Spatio-Textual Representation for Controllable Image Generation","created":"2022-11-25","cited_by_count":217},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179},{"id":"2402.03290","title":"InstanceDiffusion: Instance-level Control for Image Generation","created":"2024-02-05","cited_by_count":175},{"id":"2306.08877","title":"Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment","created":"2023-06-15","cited_by_count":171},{"id":"2306.05427","title":"Grounded Text-to-Image Synthesis with Attention Refocusing","created":"2023-06-08","cited_by_count":164},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127},{"id":"2310.03502","title":"Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion","created":"2023-10-05","cited_by_count":114},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97},{"id":"2304.05390","title":"HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models","created":"2023-04-11","cited_by_count":95},{"id":"2307.10864","title":"Divide & Bind Your Attention for Improved Generative Semantic Nursing","created":"2023-07-20","cited_by_count":81},{"id":"2306.14544","title":"A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis","created":"2023-06-26","cited_by_count":78},{"id":"2302.08908","title":"LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation","created":"2023-02-16","cited_by_count":65},{"id":"2404.14743","title":"Gradient Guidance for Diffusion Models: An Optimization Perspective","created":"2024-04-23","cited_by_count":61},{"id":"2303.12074","title":"CC3D: Layout-Conditioned Generation of Compositional 3D Scenes","created":"2023-03-21","cited_by_count":58},{"id":"2406.10210","title":"Make It Count: Text-to-Image Generation with an Accurate Number of Objects","created":"2024-06-14","cited_by_count":47},{"id":"2305.13308","title":"If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection","created":"2023-05-22","cited_by_count":40},{"id":"2411.07132","title":"Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis","created":"2024-11-11","cited_by_count":35},{"id":"2404.01197","title":"Getting it Right: Improving Spatial Consistency in Text-to-Image Models","created":"2024-04-01","cited_by_count":30},{"id":"2403.06381","title":"Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models","created":"2024-03-11","cited_by_count":27},{"id":"2410.20474","title":"GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation","created":"2024-10-27","cited_by_count":24},{"id":"2402.12908","title":"RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models","created":"2024-02-20","cited_by_count":18},{"id":"2311.16117","title":"Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models","created":"2023-10-03","cited_by_count":16},{"id":"2312.06038","title":"Correcting Diffusion Generation through Resampling","created":"2023-12-10","cited_by_count":15},{"id":"2412.17622","title":"Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms","created":"2024-12-23","cited_by_count":14},{"id":"2404.04544","title":"BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion","created":"2024-04-06","cited_by_count":9},{"id":"2410.22775","title":"Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models","created":"2024-10-30","cited_by_count":5}],"next_cursor":null}