{"total":209,"rows":[{"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":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288,"area":"lr"},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200,"area":null},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"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":"2307.11795","title":"Prompting Large Language Models with Speech Recognition Abilities","created":"2023-07-21","cited_by_count":140,"area":null},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117,"area":"lr"},{"id":"2402.01801","title":"Large Language Models for Time Series: A Survey","created":"2024-02-02","cited_by_count":114,"area":null},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110,"area":"lr"},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103,"area":"lr"},{"id":"2409.15272","title":"OmniBench: Towards The Future of Universal Omni-Language Models","created":"2024-09-23","cited_by_count":102,"area":"mllm"},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101,"area":null},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"area":null},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94,"area":null},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80,"area":null},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79,"area":"synth"},{"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":"2310.09424","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","created":"2023-10-13","cited_by_count":76,"area":null},{"id":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","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":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"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":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2506.15220","title":"video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models","created":"2025-06-18","cited_by_count":47,"area":null},{"id":"2412.10523","title":"The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion","created":"2024-12-13","cited_by_count":46,"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":"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":"2409.20007","title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data","created":"2024-09-30","cited_by_count":45,"area":null},{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39,"area":null},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2412.08608","title":"AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models","created":"2024-12-11","cited_by_count":38,"area":"safety"},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36,"area":"lr"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"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":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34,"area":null},{"id":"2406.18871","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","created":"2024-06-27","cited_by_count":33,"area":null},{"id":"2411.18138","title":"SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation","created":"2024-11-27","cited_by_count":33,"area":"mllm"},{"id":"2311.02248","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","created":"2023-11-03","cited_by_count":31,"area":"mllm"},{"id":"2410.16130","title":"Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning","created":"2024-10-21","cited_by_count":31,"area":"lr"},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2407.09886","title":"Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation","created":"2024-07-13","cited_by_count":27,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2503.08540","title":"Mellow: a small audio language model for reasoning","created":"2025-03-11","cited_by_count":27,"area":"lr"},{"id":"2505.17060","title":"SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation","created":"2025-05-17","cited_by_count":27,"area":null},{"id":"2407.01851","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","created":"2024-07-01","cited_by_count":26,"area":"mllm"},{"id":"2403.12736","title":"Towards Multimodal In-Context Learning for Vision & Language Models","created":"2024-03-19","cited_by_count":25,"area":"mllm"},{"id":"2310.05863","title":"Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models","created":"2023-10-09","cited_by_count":21,"area":"mllm"},{"id":"2412.12009","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","created":"2024-12-16","cited_by_count":21,"area":"inference"},{"id":"2505.15406","title":"Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models","created":"2025-05-21","cited_by_count":21,"area":"safety"},{"id":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2410.04534","title":"UniMuMo: Unified Text, Music and Motion Generation","created":"2024-10-06","cited_by_count":19,"area":null},{"id":"2510.07978","title":"VoiceAgentBench: Are Voice Assistants ready for agentic tasks?","created":"2025-10-09","cited_by_count":19,"area":"agents"},{"id":"2604.10905","title":"Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music","created":"2026-04-13","cited_by_count":19,"area":null},{"id":"2405.13684","title":"CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models","created":"2024-05-22","cited_by_count":18,"area":null},{"id":"2410.01162","title":"Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2506.05140","title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","created":"2025-06-05","cited_by_count":18,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17,"area":null},{"id":"2409.04927","title":"Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue","created":"2024-09-07","cited_by_count":16,"area":"lr"},{"id":"2410.12219","title":"OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities","created":"2024-10-16","cited_by_count":16,"area":"lr"},{"id":"2309.04842","title":"Leveraging Large Language Models for Exploiting ASR Uncertainty","created":"2023-09-09","cited_by_count":15,"area":null},{"id":"2506.05414","title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing","created":"2025-06-04","cited_by_count":15,"area":"lr"},{"id":"2508.02018","title":"SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models","created":"2025-08-04","cited_by_count":14,"area":"lr"},{"id":"2405.02132","title":"Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets","created":"2024-05-03","cited_by_count":13,"area":null},{"id":"2408.16221","title":"SSDM: Scalable Speech Dysfluency Modeling","created":"2024-08-29","cited_by_count":13,"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":"2509.21625","title":"Guiding Audio Editing with Audio Language Model","created":"2025-09-25","cited_by_count":12,"area":"diffusion"},{"id":"2510.23451","title":"Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences","created":"2025-10-27","cited_by_count":11,"area":"alignment"},{"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":"2410.13839","title":"Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding","created":"2024-10-17","cited_by_count":10,"area":"inference"},{"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":"2509.26140","title":"OWL: Geometry-Aware Spatial Reasoning for Audio Large Language Models","created":"2025-09-30","cited_by_count":10,"area":"lr"},{"id":"2310.02050","title":"Tuning Large language model for End-to-end Speech Translation","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2407.03169","title":"Investigating Decoder-only Large Language Models for Speech-to-text Translation","created":"2024-07-03","cited_by_count":9,"area":"lr"},{"id":"2410.15573","title":"OpenMU: Your Swiss Army Knife for Music Understanding","created":"2024-10-21","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":"2601.05543","title":"Closing the Modality Reasoning Gap for Speech Large Language Models","created":"2026-01-09","cited_by_count":9,"area":"lr"},{"id":"2406.11025","title":"Large Language Models for Dysfluency Detection in Stuttered Speech","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2410.06682","title":"Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization","created":"2024-10-09","cited_by_count":8,"area":"mllm"},{"id":"2412.09818","title":"MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models","created":"2024-12-13","cited_by_count":8,"area":"lr"},{"id":"2505.01199","title":"CaReAQA: A Cardiac and Respiratory Audio Question Answering Model for Open-Ended Diagnostic Reasoning","created":"2025-05-02","cited_by_count":8,"area":"lr"},{"id":"2309.09843","title":"Instruction-Following Speech Recognition","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2505.20166","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","created":"2025-05-26","cited_by_count":7,"area":"synth"},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2509.21990","title":"WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM","created":"2025-09-26","cited_by_count":7,"area":"mllm"},{"id":"2512.10403","title":"BRACE: A Benchmark for Robust Audio Caption Quality Evaluation","created":"2025-12-11","cited_by_count":7,"area":null},{"id":"2310.07284","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","created":"2023-10-11","cited_by_count":6,"area":null}],"next_cursor":"100"}