{"list":"other","total":62,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"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":"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":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2012.00926","title":"pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis","created":"2020-12-02","cited_by_count":708},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"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":"1906.12320","title":"PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows","created":"2019-06-28","cited_by_count":488},{"id":"2209.11163","title":"GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images","created":"2022-09-22","cited_by_count":446},{"id":"2505.07818","title":"DanceGRPO: Unleashing GRPO on Visual Generation","created":"2025-05-12","cited_by_count":413},{"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":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2507.21802","title":"MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE","created":"2025-07-29","cited_by_count":178},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2504.12369","title":"WorldMem: Long-term Consistent World Simulation with Memory","created":"2025-04-16","cited_by_count":168},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154},{"id":"2504.12626","title":"Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models","created":"2025-04-17","cited_by_count":143},{"id":"2312.10240","title":"Rich Human Feedback for Text-to-Image Generation","created":"2023-12-15","cited_by_count":141},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136},{"id":"2410.15957","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","created":"2024-10-21","cited_by_count":120},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","cited_by_count":117},{"id":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103},{"id":"2409.12957","title":"3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion","created":"2024-09-19","cited_by_count":101},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98},{"id":"2501.06336","title":"MEt3R: Measuring Multi-View Consistency in Generated Images","created":"2025-01-10","cited_by_count":95},{"id":"2508.21058","title":"Mixture of Contexts for Long Video Generation","created":"2025-08-28","cited_by_count":95},{"id":"2402.10210","title":"Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation","created":"2024-02-15","cited_by_count":85},{"id":"2505.20171","title":"Long-Context State-Space Video World Models","created":"2025-05-26","cited_by_count":64},{"id":"2506.21526","title":"WAFT: Warping-Alone Field Transforms for Optical Flow","created":"2025-06-26","cited_by_count":34},{"id":"2404.12389","title":"Moving Object Segmentation: All You Need Is SAM (and Flow)","created":"2024-04-18","cited_by_count":30},{"id":"2512.12080","title":"BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models","created":"2025-12-12","cited_by_count":16},{"id":"2411.13549","title":"KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos","created":"2024-11-20","cited_by_count":7},{"id":"2512.02793","title":"IC-World: In-Context Generation for Shared World Modeling","created":"2025-12-01","cited_by_count":6}],"next_cursor":null}