{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2305.03495","title":"Automatic Prompt Optimization with \"Gradient Descent\" and Beam Search","created":"2023-05-04","cited_by_count":653},{"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":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"2011.01403","title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning","created":"2020-11-03","cited_by_count":276},{"id":"2212.06909","title":"Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting","created":"2022-12-13","cited_by_count":233},{"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":"2211.08332","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","created":"2022-11-15","cited_by_count":199},{"id":"2309.08532","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","created":"2023-09-15","cited_by_count":193},{"id":"2305.18274","title":"Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors","created":"2023-05-29","cited_by_count":160},{"id":"2211.06956","title":"Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding","created":"2022-11-13","cited_by_count":144},{"id":"2203.07281","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","created":"2022-03-14","cited_by_count":127},{"id":"1510.06479","title":"Generic decoding of seen and imagined objects using hierarchical visual features","created":"2015-10-22","cited_by_count":120},{"id":"2403.11207","title":"MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data","created":"2024-03-17","cited_by_count":109},{"id":"2210.01769","title":"Mind Reader: Reconstructing complex images from brain activities","created":"2022-09-30","cited_by_count":85},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68},{"id":"2404.07850","title":"MindBridge: A Cross-Subject Brain Decoding Framework","created":"2024-04-11","cited_by_count":66},{"id":"1809.01281","title":"BOLD5000: A public fMRI dataset of 5000 images","created":"2018-09-05","cited_by_count":63},{"id":"2210.06756","title":"Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features","created":"2022-10-13","cited_by_count":63},{"id":"2202.12692","title":"Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANs","created":"2022-02-25","cited_by_count":55},{"id":"2211.11890","title":"TEMPERA: Test-Time Prompting via Reinforcement Learning","created":"2022-11-21","cited_by_count":50},{"id":"2212.10539","title":"Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?","created":"2022-12-20","cited_by_count":49},{"id":"2308.04249","title":"MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion","created":"2023-08-08","cited_by_count":47},{"id":"2310.02265","title":"DREAM: Visual Decoding from Reversing Human Visual System","created":"2023-10-03","cited_by_count":44},{"id":"2305.17214","title":"Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities","created":"2023-05-26","cited_by_count":36},{"id":"2404.12630","title":"MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction","created":"2024-04-19","cited_by_count":32},{"id":"2305.19638","title":"A Unified Framework for U-Net Design and Analysis","created":"2023-05-31","cited_by_count":27},{"id":"2410.19452","title":"NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction","created":"2024-10-25","cited_by_count":26},{"id":"2403.20022","title":"Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity","created":"2024-03-29","cited_by_count":22},{"id":"2310.04420","title":"BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity","created":"2023-10-06","cited_by_count":19},{"id":"2405.01012","title":"Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networks","created":"2024-05-02","cited_by_count":18},{"id":"2312.06038","title":"Correcting Diffusion Generation through Resampling","created":"2023-12-10","cited_by_count":15},{"id":"2401.00430","title":"Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy","created":"2023-12-31","cited_by_count":15},{"id":"2502.15786","title":"MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding","created":"2025-02-18","cited_by_count":14},{"id":"2402.13809","title":"NeuralDiffuser: Neuroscience-inspired Diffusion Guidance for fMRI Visual Reconstruction","created":"2024-02-21","cited_by_count":10},{"id":"2112.09305","title":"Gaussian RBF Centered Kernel Alignment (CKA) in the Large Bandwidth Limit","created":"2021-12-17","cited_by_count":6},{"id":"2411.07121","title":"Decoding Visual Experience and Mapping Semantics through Whole-Brain Analysis Using fMRI Foundation Models","created":"2024-11-11","cited_by_count":6},{"id":"2406.02659","title":"Reanimating Images using Neural Representations of Dynamic Stimuli","created":"2024-06-04","cited_by_count":5},{"id":"1706.04215","title":"Identifying Spatial Relations in Images using Convolutional Neural Networks","created":"2017-06-13","cited_by_count":4},{"id":"2409.14021","title":"BrainDreamer: Reasoning-Coherent and Controllable Image Generation from EEG Brain Signals via Language Guidance","created":"2024-09-21","cited_by_count":4}],"next_cursor":null}