{"list":"other","total":70,"rows":[{"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":"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"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":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"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":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"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":"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":"2303.08797","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","created":"2023-03-15","cited_by_count":939},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135},{"id":"2312.06640","title":"Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution","created":"2023-12-11","cited_by_count":132},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123},{"id":"1802.05642","title":"The Mechanics of n-Player Differentiable Games","created":"2018-02-15","cited_by_count":118},{"id":"2312.09109","title":"VideoLCM: Video Latent Consistency Model","created":"2023-12-14","cited_by_count":92},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81},{"id":"1408.3060","title":"Fastfood: Approximate Kernel Expansions in Loglinear Time","created":"2014-08-13","cited_by_count":74},{"id":"1802.09419","title":"Stochastic Hyperparameter Optimization through Hypernetworks","created":"2018-02-26","cited_by_count":73},{"id":"2408.02629","title":"VidGen-1M: A Large-Scale Dataset for Text-to-video Generation","created":"2024-08-05","cited_by_count":62},{"id":"2305.18583","title":"Controllable Text-to-Image Generation with GPT-4","created":"2023-05-29","cited_by_count":59},{"id":"2406.08850","title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","created":"2024-06-13","cited_by_count":59},{"id":"2506.07310","title":"AllTracker: Efficient Dense Point Tracking at High Resolution","created":"2025-06-08","cited_by_count":58},{"id":"2305.13840","title":"Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning","created":"2023-05-23","cited_by_count":48},{"id":"2311.00500","title":"Intriguing Properties of Data Attribution on Diffusion Models","created":"2023-11-01","cited_by_count":47},{"id":"2306.09345","title":"Evaluating Data Attribution for Text-to-Image Models","created":"2023-06-15","cited_by_count":45},{"id":"2312.06205","title":"The Journey, Not the Destination: How Data Guides Diffusion Models","created":"2023-12-11","cited_by_count":43},{"id":"2401.11739","title":"EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models","created":"2024-01-22","cited_by_count":43},{"id":"2508.13154","title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy","created":"2025-08-18","cited_by_count":34},{"id":"2410.13850","title":"Influence Functions for Scalable Data Attribution in Diffusion Models","created":"2024-10-17","cited_by_count":33},{"id":"2512.08931","title":"Astra: General Interactive World Model with Autoregressive Denoising","created":"2025-12-09","cited_by_count":33},{"id":"2212.14032","title":"On Implicit Bias in Overparameterized Bilevel Optimization","created":"2022-12-28","cited_by_count":30},{"id":"2405.03875","title":"Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits","created":"2024-05-06","cited_by_count":29},{"id":"2501.00654","title":"ICONS: Influence Consensus for Vision-Language Data Selection","created":"2024-12-31","cited_by_count":29},{"id":"2111.01754","title":"Meta-Learning to Improve Pre-Training","created":"2021-11-02","cited_by_count":27},{"id":"2502.12089","title":"How Compositional Generalization and Creativity Improve as Diffusion Models are Trained","created":"2025-02-17","cited_by_count":25},{"id":"2410.18639","title":"Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models","created":"2024-10-24","cited_by_count":22},{"id":"2411.08034","title":"Scaling Properties of Diffusion Models for Perceptual Tasks","created":"2024-11-12","cited_by_count":15},{"id":"2401.09031","title":"Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation","created":"2024-01-17","cited_by_count":14},{"id":"2503.17350","title":"Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer","created":"2025-03-21","cited_by_count":14},{"id":"2311.00353","title":"LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video Translation","created":"2023-11-01","cited_by_count":12},{"id":"2102.08431","title":"Complex Momentum for Optimization in Games","created":"2021-02-16","cited_by_count":11},{"id":"2410.23274","title":"Multi-student Diffusion Distillation for Better One-step Generators","created":"2024-10-30","cited_by_count":10},{"id":"2112.14570","title":"Lyapunov Exponents for Diversity in Differentiable Games","created":"2021-12-24","cited_by_count":8},{"id":"2208.12754","title":"Task Selection for AutoML System Evaluation","created":"2022-08-26","cited_by_count":7},{"id":"2408.13237","title":"JacNet: Learning Functions with Structured Jacobians","created":"2024-08-23","cited_by_count":7},{"id":"2511.10721","title":"Fast Data Attribution for Text-to-Image Models","created":"2025-11-13","cited_by_count":7},{"id":"2505.04621","title":"Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond","created":"2025-05-07","cited_by_count":6},{"id":"2406.18630","title":"Improving Hyperparameter Optimization with Checkpointed Model Weights","created":"2024-06-26","cited_by_count":5},{"id":"2407.01526","title":"Scalable Nested Optimization for Deep Learning","created":"2024-07-01","cited_by_count":3},{"id":"2507.06547","title":"Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution","created":"2025-07-09","cited_by_count":3}],"next_cursor":null}