{"list":"other","total":135,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"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":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"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":"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":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"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":"2403.05135","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","created":"2024-03-08","cited_by_count":475},{"id":"2401.07519","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","created":"2024-01-15","cited_by_count":436},{"id":"2409.11340","title":"OmniGen: Unified Image Generation","created":"2024-09-17","cited_by_count":394},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"2403.04692","title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","created":"2024-03-07","cited_by_count":329},{"id":"2405.08748","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","created":"2024-05-14","cited_by_count":298},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"2403.12015","title":"Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation","created":"2024-03-18","cited_by_count":279},{"id":"1610.06545","title":"Revisiting Classifier Two-Sample Tests","created":"2016-10-20","cited_by_count":268},{"id":"2303.07909","title":"Text-to-image Diffusion Models in Generative AI: A Survey","created":"2023-03-14","cited_by_count":265},{"id":"2210.04610","title":"Red-Teaming the Stable Diffusion Safety Filter","created":"2022-10-03","cited_by_count":264},{"id":"2402.17245","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","created":"2024-02-27","cited_by_count":256},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"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":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201},{"id":"2309.17102","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","created":"2023-09-29","cited_by_count":185},{"id":"2309.02591","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning","created":"2023-09-05","cited_by_count":170},{"id":"2311.03054","title":"AnyText: Multilingual Visual Text Generation And Editing","created":"2023-11-06","cited_by_count":170},{"id":"2404.02733","title":"InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation","created":"2024-04-03","cited_by_count":170},{"id":"2302.04578","title":"Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples","created":"2023-02-09","cited_by_count":167},{"id":"2408.06070","title":"ControlNeXt: Powerful and Efficient Control for Image and Video Generation","created":"2024-08-12","cited_by_count":159},{"id":"2401.05252","title":"PIXART-{\\delta}: Fast and Controllable Image Generation with Latent Consistency Models","created":"2024-01-10","cited_by_count":141},{"id":"1511.02793","title":"Generating Images from Captions with Attention","created":"2015-11-09","cited_by_count":136},{"id":"2407.12383","title":"Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models","created":"2024-07-17","cited_by_count":133},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132},{"id":"1609.02200","title":"Discrete Variational Autoencoders","created":"2016-09-07","cited_by_count":125},{"id":"2402.17113","title":"Transparent Image Layer Diffusion using Latent Transparency","created":"2024-02-27","cited_by_count":114},{"id":"2312.04965","title":"Inversion-Free Image Editing with Natural Language","created":"2023-12-07","cited_by_count":106},{"id":"2310.06313","title":"Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models","created":"2023-10-10","cited_by_count":104},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97},{"id":"2305.12683","title":"Mist: Towards Improved Adversarial Examples for Diffusion Models","created":"2023-05-22","cited_by_count":94},{"id":"2103.00823","title":"M6: A Chinese Multimodal Pretrainer","created":"2021-03-01","cited_by_count":91},{"id":"2402.10210","title":"Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation","created":"2024-02-15","cited_by_count":85},{"id":"2403.04279","title":"Controllable Generation with Text-to-Image Diffusion Models: A Survey","created":"2024-03-07","cited_by_count":83},{"id":"2309.03350","title":"Relay Diffusion: Unifying diffusion process across resolutions for image synthesis","created":"2023-09-04","cited_by_count":79},{"id":"2305.18247","title":"TaleCrafter: Interactive Story Visualization with Multiple Characters","created":"2023-05-29","cited_by_count":73},{"id":"2403.05121","title":"CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion","created":"2024-03-08","cited_by_count":72},{"id":"2202.00512","title":"Progressive Distillation for Fast Sampling of Diffusion Models","created":"2022-02-01","cited_by_count":69},{"id":"2403.16990","title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","created":"2024-03-25","cited_by_count":69},{"id":"2405.12970","title":"Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control","created":"2024-05-21","cited_by_count":67},{"id":"2404.01030","title":"Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation","created":"2024-04-01","cited_by_count":66},{"id":"2410.01699","title":"Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding","created":"2024-10-02","cited_by_count":66},{"id":"2404.03653","title":"CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching","created":"2024-04-04","cited_by_count":61},{"id":"2304.06632","title":"AI-Generated Content (AIGC): A Survey","created":"2023-03-26","cited_by_count":59},{"id":"1909.02050","title":"TIGEr: Text-to-Image Grounding for Image Caption Evaluation","created":"2019-09-04","cited_by_count":58},{"id":"2312.12491","title":"StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation","created":"2023-12-19","cited_by_count":58},{"id":"2306.00637","title":"Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models","created":"2023-06-01","cited_by_count":51},{"id":"2408.05939","title":"UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization","created":"2024-08-12","cited_by_count":47},{"id":"2407.07614","title":"MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis","created":"2024-07-10","cited_by_count":44},{"id":"2409.02097","title":"LinFusion: 1 GPU, 1 Minute, 16K Image","created":"2024-09-03","cited_by_count":43},{"id":"2312.13691","title":"DreamTuner: Single Image is Enough for Subject-Driven Generation","created":"2023-12-21","cited_by_count":41},{"id":"2312.03626","title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","created":"2023-12-06","cited_by_count":40},{"id":"2311.14284","title":"Paragraph-to-Image Generation with Information-Enriched Diffusion Model","created":"2023-11-24","cited_by_count":39},{"id":"2401.18085","title":"Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators","created":"2024-01-31","cited_by_count":39},{"id":"2311.11243","title":"AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort","created":"2023-11-19","cited_by_count":38},{"id":"2405.14785","title":"EditWorld: Simulating World Dynamics for Instruction-Following Image Editing","created":"2024-05-23","cited_by_count":38},{"id":"2401.06105","title":"PALP: Prompt Aligned Personalization of Text-to-Image Models","created":"2024-01-11","cited_by_count":35},{"id":"2404.05674","title":"MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation","created":"2024-04-08","cited_by_count":35},{"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":"2410.07171","title":"IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation","created":"2024-10-09","cited_by_count":33},{"id":"2305.13812","title":"Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality","created":"2023-05-23","cited_by_count":32},{"id":"2407.18247","title":"RegionDrag: Fast Region-Based Image Editing with Diffusion Models","created":"2024-07-25","cited_by_count":32},{"id":"2409.02543","title":"StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models","created":"2024-09-04","cited_by_count":32},{"id":"2410.08159","title":"DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation","created":"2024-10-10","cited_by_count":32},{"id":"2403.17008","title":"FlashFace: Human Image Personalization with High-fidelity Identity Preservation","created":"2024-03-25","cited_by_count":31},{"id":"2409.13346","title":"Imagine yourself: Tuning-Free Personalized Image Generation","created":"2024-09-20","cited_by_count":30}],"next_cursor":"100"}