{"list":"other","total":51,"rows":[{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2407.01284","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","created":"2024-07-01","cited_by_count":286},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"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":"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":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82},{"id":"2305.11675","title":"Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity","created":"2023-05-19","cited_by_count":71},{"id":"2404.07850","title":"MindBridge: A Cross-Subject Brain Decoding Framework","created":"2024-04-11","cited_by_count":66},{"id":"1608.03425","title":"Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision","created":"2016-08-11","cited_by_count":60},{"id":"2212.02409","title":"Decoding natural image stimuli from fMRI data with a surface-based convolutional network","created":"2022-12-05","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":"2403.18211","title":"NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation","created":"2024-03-27","cited_by_count":34},{"id":"2404.07202","title":"UMBRAE: Unified Multimodal Brain Decoding","created":"2024-04-10","cited_by_count":32},{"id":"2404.12630","title":"MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction","created":"2024-04-19","cited_by_count":32},{"id":"2410.19452","title":"NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction","created":"2024-10-25","cited_by_count":26},{"id":"2401.14535","title":"CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process","created":"2024-01-25","cited_by_count":23},{"id":"2403.20022","title":"Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity","created":"2024-03-29","cited_by_count":22},{"id":"2206.03544","title":"A Penny for Your (visual) Thoughts: Self-Supervised Reconstruction of Natural Movies from Brain Activity","created":"2022-06-07","cited_by_count":20},{"id":"2411.00492","title":"Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models","created":"2024-11-01","cited_by_count":14},{"id":"2405.03280","title":"Animate Your Thoughts: Decoupled Reconstruction of Dynamic Natural Vision from Slow Brain Activity","created":"2024-05-06","cited_by_count":11},{"id":"2412.19487","title":"UniBrain: A Unified Model for Cross-Subject Brain Decoding","created":"2024-12-27","cited_by_count":11},{"id":"2402.01590","title":"NeuroCine: Decoding Vivid Video Sequences from Human Brain Activties","created":"2024-02-02","cited_by_count":10},{"id":"2502.16861","title":"A Survey of fMRI to Image Reconstruction","created":"2025-02-24","cited_by_count":6},{"id":"2503.11167","title":"Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction","created":"2025-03-14","cited_by_count":6},{"id":"2601.17857","title":"SynMind: Reducing Semantic Hallucination in fMRI-Based Image Reconstruction","created":"2026-01-25","cited_by_count":1}],"next_cursor":null}