{"list":"other","total":56,"rows":[{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2203.15332","title":"Balanced Multimodal Learning via On-the-fly Gradient Modulation","created":"2022-03-29","cited_by_count":264},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2212.09478","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","created":"2022-12-19","cited_by_count":227},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136},{"id":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131},{"id":"2211.07089","title":"PMR: Prototypical Modal Rebalance for Multimodal Learning","created":"2022-11-14","cited_by_count":116},{"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":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110},{"id":"2401.16423","title":"Synchformer: Efficient Synchronization from Sparse Cues","created":"2024-01-29","cited_by_count":97},{"id":"2211.03089","title":"I Hear Your True Colors: Image Guided Audio Generation","created":"2022-11-06","cited_by_count":92},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69},{"id":"2411.08128","title":"CameraHMR: Aligning People with Perspective","created":"2024-11-12","cited_by_count":65},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61},{"id":"2010.10802","title":"Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies","created":"2020-10-21","cited_by_count":57},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41},{"id":"2511.03334","title":"UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions","created":"2025-11-05","cited_by_count":38},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25},{"id":"2512.21094","title":"T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation","created":"2025-12-24","cited_by_count":24},{"id":"2305.13050","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","created":"2023-05-22","cited_by_count":22},{"id":"2502.03897","title":"UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generation","created":"2025-02-06","cited_by_count":22},{"id":"2506.01144","title":"FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation","created":"2025-06-01","cited_by_count":22},{"id":"2510.26794","title":"The Quest for Generalizable Motion Generation: Data, Model, and Evaluation","created":"2025-10-30","cited_by_count":22},{"id":"2511.21579","title":"Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy","created":"2025-11-26","cited_by_count":21},{"id":"2604.08540","title":"AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation","created":"2026-04-09","cited_by_count":21},{"id":"2603.11647","title":"OmniForcing: Unleashing Real-time Joint Audio-Visual Generation","created":"2026-03-12","cited_by_count":16},{"id":"2512.18814","title":"EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer","created":"2025-12-21","cited_by_count":13},{"id":"2602.21818","title":"SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model","created":"2026-02-25","cited_by_count":12},{"id":"2407.10937","title":"IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation","created":"2024-07-15","cited_by_count":11},{"id":"2505.00482","title":"JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers","created":"2025-05-01","cited_by_count":11},{"id":"2405.18677","title":"Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering","created":"2024-05-29","cited_by_count":9},{"id":"2508.04147","title":"IDCNet: Guided Video Diffusion for Metric-Consistent RGBD Scene Generation with Precise Camera Control","created":"2025-08-06","cited_by_count":7},{"id":"2601.22143","title":"JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion","created":"2026-01-29","cited_by_count":7},{"id":"2601.10632","title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","created":"2026-01-15","cited_by_count":6},{"id":"2412.20422","title":"Bringing Objects to Life: training-free 4D generation from 3D objects through view consistent noise","created":"2024-12-29","cited_by_count":5},{"id":"2508.17404","title":"MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling","created":"2025-08-24","cited_by_count":4},{"id":"2510.03909","title":"Generating Human Motion Videos using a Cascaded Text-to-Video Framework","created":"2025-10-04","cited_by_count":4},{"id":"2603.18600","title":"Improving Joint Audio-Video Generation with Cross-Modal Context Learning","created":"2026-03-19","cited_by_count":4},{"id":"2606.03183","title":"Inference-Time Scaling for Joint Audio-Video Generation","created":"2026-06-02","cited_by_count":4},{"id":"2511.12072","title":"ProAV-DiT: A Projected Latent Diffusion Transformer for Efficient Synchronized Audio-Video Generation","created":"2025-11-15","cited_by_count":2},{"id":"2606.02000","title":"Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization","created":"2026-06-01","cited_by_count":1}],"next_cursor":null}