{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"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":"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":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340},{"id":"2401.09603","title":"Rethinking FID: Towards a Better Evaluation Metric for Image Generation","created":"2023-11-30","cited_by_count":310},{"id":"1901.06706","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","created":"2019-01-20","cited_by_count":252},{"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":"2306.08877","title":"Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment","created":"2023-06-15","cited_by_count":171},{"id":"2403.14572","title":"Implicit Style-Content Separation using B-LoRA","created":"2024-03-21","cited_by_count":135},{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122},{"id":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108},{"id":"2309.15664","title":"Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing","created":"2023-09-27","cited_by_count":76},{"id":"2403.16990","title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","created":"2024-03-25","cited_by_count":69},{"id":"2305.10853","title":"LDM3D: Latent Diffusion Model for 3D","created":"2023-05-18","cited_by_count":53},{"id":"2210.10606","title":"DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models","created":"2022-10-19","cited_by_count":51},{"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":"2410.12669","title":"3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation","created":"2024-10-16","cited_by_count":37},{"id":"2411.06558","title":"Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement","created":"2024-11-10","cited_by_count":37},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35},{"id":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31},{"id":"2411.02395","title":"Training-free Regional Prompting for Diffusion Transformers","created":"2024-11-04","cited_by_count":27},{"id":"2501.05131","title":"3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering","created":"2025-01-09","cited_by_count":21},{"id":"2504.14988","title":"Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation","created":"2025-04-21","cited_by_count":19},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18},{"id":"2408.06518","title":"Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models","created":"2024-08-12","cited_by_count":15},{"id":"2505.21488","title":"Be Decisive: Noise-Induced Layouts for Multi-Subject Generation","created":"2025-05-27","cited_by_count":10},{"id":"2410.02613","title":"NL-Eye: Abductive NLI for Images","created":"2024-10-03","cited_by_count":5},{"id":"2504.01137","title":"Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models","created":"2025-04-01","cited_by_count":4},{"id":"2504.17502","title":"RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation","created":"2025-04-24","cited_by_count":3},{"id":"2508.14814","title":"TransLight: Image-Guided Customized Lighting Control with Generative Decoupling","created":"2025-08-20","cited_by_count":2}],"next_cursor":null}