{"total":18,"rows":[{"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,"area":null},{"id":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67,"area":null},{"id":"2309.03467","title":"Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation","created":"2023-09-07","cited_by_count":33,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2311.04066","title":"Can CLIP Help Sound Source Localization?","created":"2023-11-07","cited_by_count":14,"area":null},{"id":"2409.03701","title":"LAST: Language Model Aware Speech Tokenization","created":"2024-09-05","cited_by_count":9,"area":null},{"id":"2512.10571","title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","created":"2025-12-11","cited_by_count":9,"area":null},{"id":"2404.16581","title":"AudioScenic: Audio-Driven Video Scene Editing","created":"2024-04-25","cited_by_count":5,"area":null},{"id":"2412.06209","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2503.10287","title":"MACS: Multi-source Audio-to-image Generation with Contextual Significance and Semantic Alignment","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2309.01340","title":"MDSC: Towards Evaluating the Style Consistency Between Music and Dance","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2312.05698","title":"Unsupervised Multi-modal Feature Alignment for Time Series Representation Learning","created":"2023-12-09","cited_by_count":0,"area":null},{"id":"2504.18283","title":"Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2505.12734","title":"SounDiT: Geo-Contextual Soundscape-to-Landscape Generation","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2509.09717","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2603.22732","title":"SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contexts","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2608.09529","title":"Towards Expressive and Faithful Audio-to-Image Generation: A Unified Multimodal Dataset and Synthesis Framework","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.27901","title":"All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}