{"list":"other","total":63,"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":"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"2303.11305","title":"SVDiff: Compact Parameter Space for Diffusion Fine-Tuning","created":"2023-03-20","cited_by_count":338},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2210.02410","title":"The Vendi Score: A Diversity Evaluation Metric for Machine Learning","created":"2022-10-05","cited_by_count":311},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"2309.14859","title":"Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation","created":"2023-09-26","cited_by_count":109},{"id":"1709.02480","title":"Fine-Grained Car Detection for Visual Census Estimation","created":"2017-09-07","cited_by_count":76},{"id":"2210.00990","title":"Visual Prompt Tuning for Generative Transfer Learning","created":"2022-10-03","cited_by_count":75},{"id":"2202.08625","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","created":"2022-02-17","cited_by_count":72},{"id":"2403.10701","title":"IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation","created":"2024-03-15","cited_by_count":64},{"id":"2302.14290","title":"Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation","created":"2023-02-28","cited_by_count":29},{"id":"2410.03190","title":"Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization","created":"2024-10-04","cited_by_count":26},{"id":"1802.04145","title":"DCFNet: Deep Neural Network with Decomposed Convolutional Filters","created":"2018-02-12","cited_by_count":23},{"id":"2303.10787","title":"Diffusion-based Document Layout Generation","created":"2023-03-19","cited_by_count":21},{"id":"2406.10777","title":"RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning","created":"2024-06-16","cited_by_count":21},{"id":"2409.04559","title":"Thinking Outside the BBox: Unconstrained Generative Object Compositing","created":"2024-09-06","cited_by_count":19},{"id":"2503.00306","title":"Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning","created":"2025-03-01","cited_by_count":19},{"id":"2503.06339","title":"Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning","created":"2025-03-08","cited_by_count":19},{"id":"2408.10453","title":"Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation","created":"2024-08-19","cited_by_count":16},{"id":"2307.09693","title":"GlobalMapper: Arbitrary-Shaped Urban Layout Generation","created":"2023-07-19","cited_by_count":15},{"id":"2409.08520","title":"GroundingBooth: Grounding Text-to-Image Customization","created":"2024-09-13","cited_by_count":13},{"id":"2108.07895","title":"Adaptive Convolutions with Per-pixel Dynamic Filter Atom","created":"2021-08-17","cited_by_count":11},{"id":"2403.00269","title":"Large Convolutional Model Tuning via Filter Subspace","created":"2024-03-01","cited_by_count":11},{"id":"2407.11294","title":"COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation","created":"2024-07-16","cited_by_count":10},{"id":"1909.11286","title":"Stochastic Conditional Generative Networks with Basis Decomposition","created":"2019-09-25","cited_by_count":9},{"id":"2402.11025","title":"Training Bayesian Neural Networks with Sparse Subspace Variational Inference","created":"2024-02-16","cited_by_count":7},{"id":"2412.00306","title":"Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment","created":"2024-11-30","cited_by_count":5},{"id":"2410.02147","title":"Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement","created":"2024-10-03","cited_by_count":4}],"next_cursor":null}