{"list":"other","total":59,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"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":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2305.16381","title":"DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":450},{"id":"2505.07818","title":"DanceGRPO: Unleashing GRPO on Visual Generation","created":"2025-05-12","cited_by_count":413},{"id":"2603.16666","title":"Fast-WAM: Do World Action Models Need Test-time Future Imagination?","created":"2026-03-17","cited_by_count":349},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"2501.13918","title":"Improving Video Generation with Human Feedback","created":"2025-01-23","cited_by_count":284},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2509.16117","title":"DiffusionNFT: Online Diffusion Reinforcement with Forward Process","created":"2025-09-19","cited_by_count":230},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146},{"id":"2602.06949","title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","created":"2026-02-06","cited_by_count":135},{"id":"2506.18903","title":"VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory","created":"2025-06-23","cited_by_count":109},{"id":"2504.14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","created":"2025-04-21","cited_by_count":77},{"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":"2602.13977","title":"WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL","created":"2026-02-15","cited_by_count":50},{"id":"2509.21657","title":"FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction","created":"2025-09-25","cited_by_count":38},{"id":"2512.07802","title":"OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory","created":"2025-12-08","cited_by_count":35},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35},{"id":"2512.02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models","created":"2025-12-01","cited_by_count":34},{"id":"2601.09499","title":"V-DPM: 4D Video Reconstruction with Dynamic Point Maps","created":"2026-01-14","cited_by_count":34},{"id":"2512.00425","title":"What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards","created":"2025-11-29","cited_by_count":25},{"id":"2602.09022","title":"WorldCompass: Reinforcement Learning for Long-Horizon World Models","created":"2026-02-09","cited_by_count":24},{"id":"2410.22489","title":"Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation","created":"2024-10-29","cited_by_count":20},{"id":"2601.17323","title":"SkyReels-V3 Technique Report","created":"2026-01-24","cited_by_count":20},{"id":"2506.23329","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering","created":"2025-06-29","cited_by_count":19},{"id":"2510.19022","title":"MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models","created":"2025-10-21","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":"2503.12024","title":"SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering","created":"2025-03-15","cited_by_count":15},{"id":"2511.03997","title":"PhysCorr: Dual-Reward DPO for Physics-Constrained Text-to-Video Generation with Automated Preference Selection","created":"2025-11-06","cited_by_count":15},{"id":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15},{"id":"2602.10102","title":"VideoWorld 2: Learning Transferable Knowledge from Real-world Videos","created":"2026-02-10","cited_by_count":12},{"id":"2510.13454","title":"Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator","created":"2025-10-15","cited_by_count":11},{"id":"2511.23127","title":"DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation","created":"2025-11-28","cited_by_count":11},{"id":"2501.01409","title":"JOG3R: Towards 3D-Consistent Video Generators","created":"2025-01-02","cited_by_count":9},{"id":"2512.06905","title":"Scaling Zero-Shot Reference-to-Video Generation","created":"2025-12-07","cited_by_count":9},{"id":"2511.21592","title":"MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training","created":"2025-11-26","cited_by_count":8},{"id":"2512.21338","title":"HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming","created":"2025-12-24","cited_by_count":8},{"id":"2602.21929","title":"Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context","created":"2026-02-25","cited_by_count":8},{"id":"2603.14375","title":"The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics","created":"2026-03-15","cited_by_count":8},{"id":"2603.09094","title":"Chain of Event-Centric Causal Thought for Physically Plausible Video Generation","created":"2026-03-10","cited_by_count":6},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5},{"id":"2602.08961","title":"MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE","created":"2026-02-09","cited_by_count":3}],"next_cursor":null}