{"total":526,"rows":[{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488,"area":null},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"area":null},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197,"area":null},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2401.18084","title":"Binding Touch to Everything: Learning Unified Multimodal Tactile Representations","created":"2024-01-31","cited_by_count":95,"area":null},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93,"area":null},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83,"area":null},{"id":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80,"area":null},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77,"area":null},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"area":null},{"id":"2311.10057","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","created":"2023-11-16","cited_by_count":68,"area":null},{"id":"2501.01108","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","created":"2025-01-02","cited_by_count":68,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50,"area":null},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49,"area":null},{"id":"2407.05551","title":"Read, Watch and Scream! Sound Generation from Text and Video","created":"2024-07-08","cited_by_count":48,"area":null},{"id":"2309.08730","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","created":"2023-09-15","cited_by_count":45,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2403.02682","title":"Time Weaver: A Conditional Time Series Generation Model","created":"2024-03-05","cited_by_count":37,"area":null},{"id":"2305.14381","title":"Connecting Multi-modal Contrastive Representations","created":"2023-05-22","cited_by_count":36,"area":null},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33,"area":null},{"id":"2412.09758","title":"Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals","created":"2024-12-12","cited_by_count":32,"area":null},{"id":"2512.09299","title":"VABench: A Comprehensive Benchmark for Audio-Video Generation","created":"2025-12-10","cited_by_count":30,"area":null},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2502.13128","title":"SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation","created":"2025-02-18","cited_by_count":29,"area":null},{"id":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2503.10522","title":"AudioX: A Unified Framework for Anything-to-Audio Generation","created":"2025-03-13","cited_by_count":27,"area":null},{"id":"2407.07464","title":"Video-to-Audio Generation with Hidden Alignment","created":"2024-07-10","cited_by_count":26,"area":null},{"id":"2411.11278","title":"Towards Open-Vocabulary Audio-Visual Event Localization","created":"2024-11-18","cited_by_count":26,"area":null},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25,"area":null},{"id":"2502.15602","title":"KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation","created":"2025-02-21","cited_by_count":24,"area":null},{"id":"2309.13664","title":"VoiceLDM: Text-to-Speech with Environmental Context","created":"2023-09-24","cited_by_count":23,"area":null},{"id":"2412.00175","title":"Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning","created":"2024-11-29","cited_by_count":23,"area":null},{"id":"2308.04978","title":"Transferable Models for Bioacoustics with Human Language Supervision","created":"2023-08-09","cited_by_count":21,"area":null},{"id":"2310.08884","title":"Extending Multi-modal Contrastive Representations","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2310.18709","title":"Audio-Visual Instance Segmentation","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2406.09272","title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","created":"2024-06-13","cited_by_count":21,"area":null},{"id":"2507.08557","title":"FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation","created":"2025-07-11","cited_by_count":21,"area":null},{"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,"area":null},{"id":"2406.00919","title":"Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2406.07529","title":"MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation","created":"2024-06-11","cited_by_count":20,"area":null},{"id":"2408.13608","title":"SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description","created":"2024-08-24","cited_by_count":20,"area":null},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2602.12160","title":"DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation","created":"2026-02-12","cited_by_count":20,"area":null},{"id":"2310.17162","title":"Content-based Controls For Music Large Language Modeling","created":"2023-10-26","cited_by_count":19,"area":null},{"id":"2405.04883","title":"FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2412.16526","title":"Text2midi: Generating Symbolic Music from Captions","created":"2024-12-21","cited_by_count":19,"area":null},{"id":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2404.17806","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","created":"2024-04-27","cited_by_count":18,"area":null},{"id":"2402.09508","title":"Arrange, Inpaint, and Refine: Steerable Long-term Music Audio Generation and Editing via Content-based Controls","created":"2024-02-14","cited_by_count":17,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2412.19351","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","created":"2024-12-26","cited_by_count":17,"area":null},{"id":"2408.11915","title":"Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound","created":"2024-08-21","cited_by_count":16,"area":null},{"id":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16,"area":null},{"id":"2604.18572","title":"Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale","created":"2026-04-20","cited_by_count":16,"area":null},{"id":"2310.12404","title":"Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editing","created":"2023-10-19","cited_by_count":15,"area":null},{"id":"2401.09774","title":"On the Audio Hallucinations in Large Audio-Video Language Models","created":"2024-01-18","cited_by_count":15,"area":null},{"id":"2405.18386","title":"Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning","created":"2024-05-28","cited_by_count":15,"area":null},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15,"area":null},{"id":"2411.14452","title":"Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task","created":"2024-11-11","cited_by_count":15,"area":null},{"id":"2502.07461","title":"JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2506.19085","title":"Benchmarking Music Generation Models and Metrics via Human Preference Studies","created":"2025-06-23","cited_by_count":15,"area":null},{"id":"2306.00595","title":"Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2309.10667","title":"Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping","created":"2023-09-19","cited_by_count":14,"area":null},{"id":"2311.08323","title":"The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language","created":"2023-11-14","cited_by_count":14,"area":null},{"id":"2404.16969","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","created":"2024-04-25","cited_by_count":14,"area":null},{"id":"2405.09266","title":"Dance Any Beat: Blending Beats with Visuals in Dance Video Generation","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2503.20782","title":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising","created":"2025-03-26","cited_by_count":14,"area":null},{"id":"2505.08175","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","created":"2025-05-13","cited_by_count":14,"area":null},{"id":"2508.06098","title":"MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows","created":"2025-08-08","cited_by_count":14,"area":null},{"id":"2306.13512","title":"DISCO-10M: A Large-Scale Music Dataset","created":"2023-06-23","cited_by_count":13,"area":null},{"id":"2401.14542","title":"Exploring Musical Roots: Applying Audio Embeddings to Empower Influence Attribution for a Generative Music Model","created":"2024-01-25","cited_by_count":13,"area":null},{"id":"2412.10749","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","created":"2024-12-14","cited_by_count":13,"area":null},{"id":"2412.11248","title":"Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing","created":"2024-12-15","cited_by_count":13,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2403.11780","title":"Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt","created":"2024-03-18","cited_by_count":12,"area":null},{"id":"2406.06786","title":"BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification","created":"2024-06-10","cited_by_count":12,"area":null},{"id":"2407.16564","title":"Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning","created":"2024-07-23","cited_by_count":12,"area":null},{"id":"2409.09213","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","created":"2024-09-13","cited_by_count":12,"area":null},{"id":"2410.07610","title":"CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features","created":"2024-10-10","cited_by_count":12,"area":null},{"id":"2410.13267","title":"CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models","created":"2024-10-17","cited_by_count":12,"area":null},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2411.18447","title":"Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation","created":"2024-11-27","cited_by_count":12,"area":null}],"next_cursor":"100"}