{"list":"other","total":72,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"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":"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":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"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":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141},{"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":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103},{"id":"2303.05334","title":"Natural scene reconstruction from fMRI signals using generative latent diffusion","created":"2023-03-09","cited_by_count":97},{"id":"2502.03444","title":"Masked Autoencoders Are Effective Tokenizers for Diffusion Models","created":"2025-02-05","cited_by_count":96},{"id":"2410.10306","title":"Animate-X: Universal Character Image Animation with Enhanced Motion Representation","created":"2024-10-14","cited_by_count":88},{"id":"2403.07721","title":"Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion","created":"2024-03-12","cited_by_count":81},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80},{"id":"2305.11675","title":"Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity","created":"2023-05-19","cited_by_count":71},{"id":"2310.19812","title":"Brain decoding: toward real-time reconstruction of visual perception","created":"2023-10-18","cited_by_count":66},{"id":"2404.07850","title":"MindBridge: A Cross-Subject Brain Decoding Framework","created":"2024-04-11","cited_by_count":66},{"id":"2010.06300","title":"MixCo: Mix-up Contrastive Learning for Visual Representation","created":"2020-10-13","cited_by_count":62},{"id":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61},{"id":"1608.03425","title":"Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision","created":"2016-08-11","cited_by_count":60},{"id":"2306.16934","title":"DreamDiffusion: Generating High-Quality Images from Brain EEG Signals","created":"2023-06-29","cited_by_count":56},{"id":"2410.13830","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","created":"2024-10-17","cited_by_count":43},{"id":"2302.12971","title":"BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding","created":"2023-02-25","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":"2405.05538","title":"A Survey on Personalized Content Synthesis with Diffusion Models","created":"2024-05-09","cited_by_count":29},{"id":"2410.19452","title":"NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction","created":"2024-10-25","cited_by_count":26},{"id":"2510.24711","title":"Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance","created":"2025-10-28","cited_by_count":26},{"id":"2502.14914","title":"CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness","created":"2025-02-19","cited_by_count":25},{"id":"2503.07602","title":"DreamRelation: Relation-Centric Video Customization","created":"2025-03-10","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":"2503.16036","title":"Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models","created":"2025-03-20","cited_by_count":19},{"id":"2412.03085","title":"Mimir: Improving Video Diffusion Models for Precise Text Understanding","created":"2024-12-04","cited_by_count":16},{"id":"2502.04725","title":"Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?","created":"2025-02-07","cited_by_count":15},{"id":"2507.01390","title":"FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases","created":"2025-07-02","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":"2410.05341","title":"NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping","created":"2024-10-07","cited_by_count":11},{"id":"2503.06940","title":"CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing","created":"2025-03-10","cited_by_count":11},{"id":"2507.16663","title":"Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs","created":"2025-07-22","cited_by_count":10},{"id":"2510.27128","title":"ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding","created":"2025-10-31","cited_by_count":7},{"id":"2406.17086","title":"BrainMAE: A Region-aware Self-supervised Learning Framework for Brain Signals","created":"2024-06-24","cited_by_count":6},{"id":"2409.11315","title":"MinD-3D++: Advancing fMRI-Based 3D Reconstruction with High-Quality Textured Mesh Generation and a Comprehensive Dataset","created":"2024-09-17","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":"2406.02659","title":"Reanimating Images using Neural Representations of Dynamic Stimuli","created":"2024-06-04","cited_by_count":5},{"id":"2512.13303","title":"ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement","created":"2025-12-15","cited_by_count":5},{"id":"2603.12146","title":"FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance","created":"2026-03-12","cited_by_count":5},{"id":"2603.12257","title":"DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning","created":"2026-03-12","cited_by_count":4},{"id":"2511.02565","title":"A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding","created":"2025-11-04","cited_by_count":3},{"id":"2508.02480","title":"MindShot: Multi-Shot Video Reconstruction from fMRI with LLM Decoding","created":"2025-08-04","cited_by_count":1}],"next_cursor":null}