{"list":"other","total":72,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"id":"2303.07909","title":"Text-to-image Diffusion Models in Generative AI: A Survey","created":"2023-03-14","cited_by_count":265},{"id":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264},{"id":"2503.07265","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","created":"2025-03-10","cited_by_count":204},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185},{"id":"2410.05363","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","created":"2024-10-07","cited_by_count":174},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131},{"id":"2311.01813","title":"FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation","created":"2023-11-03","cited_by_count":122},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"id":"2412.00596","title":"PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation","created":"2024-11-30","cited_by_count":80},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2407.01094","title":"Evaluation of Text-to-Video Generation Models: A Dynamics Perspective","created":"2024-07-01","cited_by_count":67},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54},{"id":"2502.17258","title":"VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing","created":"2025-02-24","cited_by_count":50},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44},{"id":"2406.08656","title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","created":"2024-06-12","cited_by_count":43},{"id":"2402.04520","title":"On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis","created":"2024-02-07","cited_by_count":41},{"id":"2312.04086","title":"MEVG: Multi-event Video Generation with Text-to-Video Models","created":"2023-12-07","cited_by_count":40},{"id":"2505.00337","title":"T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation","created":"2025-05-01","cited_by_count":39},{"id":"2412.12444","title":"LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers","created":"2024-12-17","cited_by_count":37},{"id":"2406.11802","title":"PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models","created":"2024-06-17","cited_by_count":36},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30},{"id":"2411.07602","title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","created":"2024-11-12","cited_by_count":26},{"id":"2410.10076","title":"VideoAgent: Self-Improving Video Generation","created":"2024-10-14","cited_by_count":25},{"id":"2405.16418","title":"Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective","created":"2024-05-26","cited_by_count":24},{"id":"2411.16525","title":"Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency","created":"2024-11-25","cited_by_count":22},{"id":"2411.17522","title":"On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality","created":"2024-11-26","cited_by_count":22},{"id":"2503.20672","title":"BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation","created":"2025-03-26","cited_by_count":20},{"id":"2505.01490","title":"WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation","created":"2025-05-02","cited_by_count":20},{"id":"2404.12382","title":"Lazy Diffusion Transformer for Interactive Image Editing","created":"2024-04-18","cited_by_count":19},{"id":"2503.21781","title":"VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models","created":"2025-03-27","cited_by_count":17},{"id":"2502.00688","title":"High-Order Matching for One-Step Shortcut Diffusion Models","created":"2025-02-02","cited_by_count":15},{"id":"2501.04377","title":"On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis","created":"2025-01-08","cited_by_count":14},{"id":"2502.08150","title":"Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling","created":"2025-02-12","cited_by_count":12},{"id":"2503.06884","title":"Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help","created":"2025-03-10","cited_by_count":12},{"id":"2502.00500","title":"Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation","created":"2025-02-01","cited_by_count":11},{"id":"2502.16490","title":"On Computational Limits of FlowAR Models: Expressivity and Efficiency","created":"2025-02-23","cited_by_count":10},{"id":"2503.09069","title":"Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows","created":"2025-03-12","cited_by_count":10},{"id":"2504.04051","title":"Can You Count to Nine? A Human Evaluation Benchmark for Counting Limits in Modern Text-to-Video Models","created":"2025-04-05","cited_by_count":10},{"id":"2505.04946","title":"T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models","created":"2025-05-08","cited_by_count":10},{"id":"2503.16867","title":"ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering","created":"2025-03-21","cited_by_count":9},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9},{"id":"2504.04702","title":"Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent","created":"2025-04-07","cited_by_count":8},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7},{"id":"2501.09982","title":"RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation","created":"2025-01-17","cited_by_count":6},{"id":"2503.08032","title":"HOFAR: High-Order Augmentation of Flow Autoregressive Transformers","created":"2025-03-11","cited_by_count":4},{"id":"2506.01689","title":"Respond Beyond Language: A Benchmark for Video Generation in Response to Realistic User Intents","created":"2025-06-02","cited_by_count":3},{"id":"2503.14076","title":"Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency","created":"2025-03-18","cited_by_count":2},{"id":"2405.12538","title":"Bridging the Intent Gap: Knowledge-Enhanced Visual Generation","created":"2024-05-21","cited_by_count":1}],"next_cursor":null}