{"list":"other","total":58,"rows":[{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"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":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2302.04867","title":"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models","created":"2023-02-09","cited_by_count":450},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2501.13918","title":"Improving Video Generation with Human Feedback","created":"2025-01-23","cited_by_count":284},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"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":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"2503.15558","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","created":"2025-03-18","cited_by_count":164},{"id":"2409.16283","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","created":"2024-09-24","cited_by_count":153},{"id":"2503.06800","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","created":"2025-03-09","cited_by_count":149},{"id":"2410.02416","title":"Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models","created":"2024-10-03","cited_by_count":114},{"id":"1305.6663","title":"Generalized Denoising Auto-Encoders as Generative Models","created":"2013-05-29","cited_by_count":113},{"id":"2502.02492","title":"VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models","created":"2025-02-04","cited_by_count":113},{"id":"2312.07537","title":"FreeInit: Bridging Initialization Gap in Video Diffusion Models","created":"2023-12-12","cited_by_count":95},{"id":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90},{"id":"2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","created":"2025-10-16","cited_by_count":89},{"id":"2306.14878","title":"Restart Sampling for Improving Generative Processes","created":"2023-06-26","cited_by_count":84},{"id":"2512.15840","title":"Large Video Planner Enables Generalizable Robot Control","created":"2025-12-17","cited_by_count":70},{"id":"2311.12631","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","created":"2023-11-21","cited_by_count":61},{"id":"2505.19386","title":"Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals","created":"2025-05-26","cited_by_count":53},{"id":"2503.18886","title":"CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models","created":"2025-03-24","cited_by_count":52},{"id":"2503.23368","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","created":"2025-03-30","cited_by_count":52},{"id":"2503.09595","title":"PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop","created":"2025-03-12","cited_by_count":50},{"id":"2405.13557","title":"MotionCraft: Physics-based Zero-Shot Video Generation","created":"2024-05-22","cited_by_count":48},{"id":"2412.10891","title":"Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection","created":"2024-12-14","cited_by_count":41},{"id":"2509.20358","title":"PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation","created":"2025-09-24","cited_by_count":41},{"id":"2503.18942","title":"Video-T1: Test-Time Scaling for Video Generation","created":"2025-03-24","cited_by_count":40},{"id":"2507.13428","title":"\"PhyWorldBench\": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models","created":"2025-07-17","cited_by_count":36},{"id":"2310.11142","title":"BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference","created":"2023-10-17","cited_by_count":35},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34},{"id":"2404.04243","title":"Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models","created":"2024-04-05","cited_by_count":33},{"id":"2502.00622","title":"Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling","created":"2025-02-02","cited_by_count":24},{"id":"2512.24551","title":"PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation","created":"2025-12-31","cited_by_count":23},{"id":"2506.01144","title":"FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation","created":"2025-06-01","cited_by_count":22},{"id":"2412.00205","title":"Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation","created":"2024-11-29","cited_by_count":20},{"id":"2505.21653","title":"Think Before You Diffuse: Infusing Physical Rules into Video Diffusion","created":"2025-05-27","cited_by_count":16},{"id":"2510.11512","title":"LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference","created":"2025-10-13","cited_by_count":16},{"id":"2511.21541","title":"Video Generation Models Are Good Latent Reward Models","created":"2025-11-26","cited_by_count":16},{"id":"2503.20822","title":"Synthetic Video Enhances Physical Fidelity in Video Synthesis","created":"2025-03-26","cited_by_count":15},{"id":"2512.14691","title":"MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluation","created":"2025-12-16","cited_by_count":12},{"id":"2506.07177","title":"Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models","created":"2025-06-08","cited_by_count":11},{"id":"2506.00227","title":"Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes","created":"2025-05-30","cited_by_count":5}],"next_cursor":null}