{"total":286,"rows":[{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608,"area":null},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560,"area":null},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"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":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"area":null},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"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":"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":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"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":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"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":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87,"area":null},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86,"area":null},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85,"area":null},{"id":"2502.04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","created":"2025-02-06","cited_by_count":83,"area":null},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66,"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":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2107.09817","title":"Audio Captioning Transformer","created":"2021-07-21","cited_by_count":55,"area":null},{"id":"2203.15147","title":"Separate What You Describe: Language-Queried Audio Source Separation","created":"2022-03-28","cited_by_count":45,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","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":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2305.14381","title":"Connecting Multi-modal Contrastive Representations","created":"2023-05-22","cited_by_count":36,"area":null},{"id":"2209.14275","title":"Audio Retrieval with WavText5K and CLAP Training","created":"2022-09-28","cited_by_count":35,"area":null},{"id":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34,"area":null},{"id":"2110.04684","title":"Can Audio Captions Be Evaluated with Image Caption Metrics?","created":"2021-10-10","cited_by_count":33,"area":null},{"id":"2208.12208","title":"Contrastive Audio-Language Learning for Music","created":"2022-08-25","cited_by_count":33,"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":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","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":"2307.14335","title":"WavJourney: Compositional Audio Creation with Large Language Models","created":"2023-07-26","cited_by_count":27,"area":null},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27,"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":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2501.17202","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","created":"2025-01-27","cited_by_count":25,"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":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","cited_by_count":23,"area":null},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23,"area":null},{"id":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2308.02560","title":"From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion","created":"2023-08-02","cited_by_count":22,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2310.11612","title":"Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks","created":"2023-10-17","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":"2503.14963","title":"Continual Multimodal Contrastive Learning","created":"2025-03-19","cited_by_count":20,"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":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","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":"2112.08995","title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","created":"2021-12-16","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":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"area":null},{"id":"2507.02915","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","created":"2025-06-25","cited_by_count":17,"area":null},{"id":"2107.09990","title":"CL4AC: A Contrastive Loss for Audio Captioning","created":"2021-07-21","cited_by_count":16,"area":null},{"id":"2506.16895","title":"With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You","created":"2025-06-20","cited_by_count":16,"area":null},{"id":"2203.15526","title":"Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning","created":"2022-03-29","cited_by_count":15,"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":"2510.00050","title":"Object-AVEdit: An Object-level Audio-Visual Editing Model","created":"2025-09-27","cited_by_count":14,"area":null},{"id":"2210.16428","title":"Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention","created":"2022-10-28","cited_by_count":13,"area":null},{"id":"2305.17993","title":"Multi-Scale Attention for Audio Question Answering","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2505.19663","title":"A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?","created":"2025-05-26","cited_by_count":13,"area":null},{"id":"2508.15407","title":"When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models","created":"2025-08-21","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":"2108.04692","title":"Automated Audio Captioning using Transfer Learning and Reconstruction Latent Space Similarity Regularization","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2507.19054","title":"Closing the Modality Gap for Mixed Modality Search","created":"2025-07-25","cited_by_count":12,"area":null},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11,"area":null},{"id":"2312.10144","title":"Data-Efficient Multimodal Fusion on a Single GPU","created":"2023-12-15","cited_by_count":11,"area":null},{"id":"2505.03054","title":"BLAB: Brutally Long Audio Bench","created":"2025-05-05","cited_by_count":11,"area":null},{"id":"2505.19203","title":"EnvSDD: Benchmarking Environmental Sound Deepfake Detection","created":"2025-05-25","cited_by_count":11,"area":null},{"id":"2601.02731","title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","created":"2026-01-06","cited_by_count":11,"area":null},{"id":"2203.13645","title":"Audio-text Retrieval in Context","created":"2022-03-25","cited_by_count":10,"area":null},{"id":"2405.10084","title":"Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2409.10999","title":"Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models","created":"2024-09-17","cited_by_count":10,"area":null},{"id":"2504.02061","title":"Aligned Better, Listen Better for Audio-Visual Large Language Models","created":"2025-04-02","cited_by_count":10,"area":null},{"id":"2506.11350","title":"GLAP: General contrastive audio-text pretraining across domains and languages","created":"2025-06-12","cited_by_count":10,"area":null},{"id":"2305.09690","title":"A Whisper transformer for audio captioning trained with synthetic captions and transfer learning","created":"2023-05-15","cited_by_count":9,"area":null},{"id":"2505.07609","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2604.02605","title":"Do Audio-Visual Large Language Models Really See and Hear?","created":"2026-04-03","cited_by_count":9,"area":null},{"id":"2309.12242","title":"Weakly-supervised Automated Audio Captioning via text only training","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2510.04577","title":"Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers","created":"2025-10-06","cited_by_count":8,"area":null}],"next_cursor":"100"}