{"list":"other","total":54,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"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":"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"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":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185},{"id":"2311.03054","title":"AnyText: Multilingual Visual Text Generation And Editing","created":"2023-11-06","cited_by_count":170},{"id":"2305.18259","title":"GlyphControl: Glyph Conditional Control for Visual Text Generation","created":"2023-05-29","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":"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":"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":"2312.12232","title":"Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model","created":"2023-12-19","cited_by_count":41},{"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":"2312.03626","title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","created":"2023-12-06","cited_by_count":40},{"id":"2407.01079","title":"On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)","created":"2024-07-01","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":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31},{"id":"2308.11606","title":"StoryBench: A Multifaceted Benchmark for Continuous Story Visualization","created":"2023-08-22","cited_by_count":29},{"id":"2411.07602","title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","created":"2024-11-12","cited_by_count":26},{"id":"2406.05871","title":"OmniControlNet: Dual-stage Integration for Conditional Image Generation","created":"2024-06-09","cited_by_count":24},{"id":"2310.16305","title":"Dolfin: Diffusion Layout Transformers without Autoencoder","created":"2023-10-25","cited_by_count":23},{"id":"2407.14138","title":"Visual Text Generation in the Wild","created":"2024-07-19","cited_by_count":22},{"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":"2412.06148","title":"The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity","created":"2024-12-09","cited_by_count":21},{"id":"2503.20672","title":"BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation","created":"2025-03-26","cited_by_count":20},{"id":"2310.18332","title":"WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models","created":"2023-10-20","cited_by_count":15},{"id":"2502.00688","title":"High-Order Matching for One-Step Shortcut Diffusion Models","created":"2025-02-02","cited_by_count":15},{"id":"2501.06444","title":"On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective","created":"2025-01-11","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":"2401.11094","title":"TypeDance: Creating Semantic Typographic Logos from Image through Personalized Generation","created":"2024-01-20","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":"2412.05562","title":"Modern Hopfield Networks Require Chain-of-Thought to Solve $\\mathsf{NC}^1$-Hard Problems","created":"2024-12-07","cited_by_count":9},{"id":"2412.06061","title":"Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond","created":"2024-12-08","cited_by_count":8},{"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":"2412.20984","title":"Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies","created":"2024-12-30","cited_by_count":7},{"id":"2406.17777","title":"Text-Animator: Controllable Visual Text Video Generation","created":"2024-06-25","cited_by_count":4},{"id":"2503.08032","title":"HOFAR: High-Order Augmentation of Flow Autoregressive Transformers","created":"2025-03-11","cited_by_count":4},{"id":"2410.18823","title":"Towards Visual Text Design Transfer Across Languages","created":"2024-10-24","cited_by_count":1}],"next_cursor":null}