{"total":20,"rows":[{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228,"area":null},{"id":"2303.17959","title":"Diffusion Action Segmentation","created":"2023-03-31","cited_by_count":74,"area":null},{"id":"2309.02285","title":"PromptTTS 2: Describing and Generating Voices with Text Prompt","created":"2023-09-05","cited_by_count":48,"area":null},{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"area":null},{"id":"2309.15117","title":"Generating Visual Scenes from Touch","created":"2023-09-26","cited_by_count":26,"area":null},{"id":"2504.14906","title":"OmniAudio: Generating Spatial Audio from 360-Degree Video","created":"2025-04-21","cited_by_count":17,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"area":null},{"id":"2403.11395","title":"Automated data processing and feature engineering for deep learning and big data applications: a survey","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2405.08674","title":"Expensive Multi-Objective Bayesian Optimization Based on Diffusion Models","created":"2024-05-14","cited_by_count":10,"area":null},{"id":"2311.07414","title":"FIRST: A Million-Entry Dataset for Text-Driven Fashion Synthesis and Design","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2211.00878","title":"Neural Fourier Shift for Binaural Speech Rendering","created":"2022-11-02","cited_by_count":3,"area":null},{"id":"2311.07630","title":"Cross-modal Generative Model for Visual-Guided Binaural Stereo Generation","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2412.08356","title":"Zero-Shot Mono-to-Binaural Speech Synthesis","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2211.02301","title":"Binaural Rendering of Ambisonic Signals by Neural Networks","created":"2022-11-04","cited_by_count":0,"area":null},{"id":"2307.10994","title":"Progressive distillation diffusion for raw music generation","created":"2023-07-20","cited_by_count":0,"area":null},{"id":"2503.12806","title":"AV-Surf: Surface-Enhanced Geometry-Aware Novel-View Acoustic Synthesis","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2507.16564","title":"TTMBA: Towards Text To Multiple Sources Binaural Audio Generation","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2601.01914","title":"Learning Action Hierarchies via Hybrid Geometric Diffusion","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2607.27775","title":"RIPPLE: Generating Multi-Channel Phase, Not Recovering It","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.02504","title":"SR-Edit: Region-Aware Image Editing via Self-Refinement","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}