{"list":"other","total":56,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2503.10615","title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","created":"2025-03-13","cited_by_count":370},{"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},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"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":"2503.07265","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","created":"2025-03-10","cited_by_count":204},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181},{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179},{"id":"2311.13398","title":"Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images","created":"2023-11-22","cited_by_count":173},{"id":"2206.03001","title":"PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System","created":"2022-06-07","cited_by_count":106},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97},{"id":"2406.09358","title":"Understanding Hallucinations in Diffusion Models through Mode Interpolation","created":"2024-06-13","cited_by_count":91},{"id":"2402.03190","title":"Unified Hallucination Detection for Multimodal Large Language Models","created":"2024-02-05","cited_by_count":75},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52},{"id":"2406.07546","title":"Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?","created":"2024-06-11","cited_by_count":52},{"id":"2306.01879","title":"Revisiting the Role of Language Priors in Vision-Language Models","created":"2023-06-02","cited_by_count":50},{"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":"2412.18605","title":"Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models","created":"2024-12-24","cited_by_count":45},{"id":"2305.14897","title":"Text encoders bottleneck compositionality in contrastive vision-language models","created":"2023-05-24","cited_by_count":34},{"id":"2511.22018","title":"MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis","created":"2025-11-27","cited_by_count":32},{"id":"2404.01197","title":"Getting it Right: Improving Spatial Consistency in Text-to-Image Models","created":"2024-04-01","cited_by_count":30},{"id":"2412.01243","title":"Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation","created":"2024-12-02","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":"2511.22033","title":"Pathology-Aware Prototype Evolution via LLM-Driven Semantic Disambiguation for Multicenter Diabetic Retinopathy Diagnosis","created":"2025-11-27","cited_by_count":22},{"id":"2403.05168","title":"Enhancing Multimodal Unified Representations for Cross Modal Generalization","created":"2024-03-08","cited_by_count":12},{"id":"2504.02312","title":"OmniCam: Unified Multimodal Video Generation via Camera Control","created":"2025-04-03","cited_by_count":9},{"id":"2507.03304","title":"Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations","created":"2025-07-04","cited_by_count":9},{"id":"2509.08628","title":"LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation","created":"2025-09-10","cited_by_count":7},{"id":"2410.06055","title":"RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation","created":"2024-10-08","cited_by_count":6},{"id":"2603.01010","title":"GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis","created":"2026-03-01","cited_by_count":2}],"next_cursor":null}