{"total":149,"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":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560,"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":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"area":null},{"id":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145,"area":null},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"area":null},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109,"area":null},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"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":"2502.17239","title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","created":"2025-02-24","cited_by_count":68,"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":"2412.11102","title":"Empowering LLMs to Understand and Generate Complex Vector Graphics","created":"2024-12-15","cited_by_count":66,"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":"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":"2402.12786","title":"Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations","created":"2024-02-20","cited_by_count":45,"area":null},{"id":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44,"area":null},{"id":"2410.08565","title":"Baichuan-Omni Technical Report","created":"2024-10-11","cited_by_count":42,"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":"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":"2406.18871","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","created":"2024-06-27","cited_by_count":33,"area":null},{"id":"2406.08402","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models","created":"2024-06-12","cited_by_count":31,"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":"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":"2406.02092","title":"MaskSR: Masked Language Model for Full-band Speech Restoration","created":"2024-06-04","cited_by_count":24,"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":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23,"area":null},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22,"area":null},{"id":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22,"area":null},{"id":"2310.04445","title":"LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model","created":"2023-10-02","cited_by_count":21,"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":"2401.17851","title":"Instruction-Guided Scene Text Recognition","created":"2024-01-31","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":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17,"area":null},{"id":"2309.04842","title":"Leveraging Large Language Models for Exploiting ASR Uncertainty","created":"2023-09-09","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":"2308.10390","title":"LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models","created":"2023-08-20","cited_by_count":14,"area":null},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","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":"2409.07841","title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models","created":"2024-09-12","cited_by_count":10,"area":null},{"id":"2406.11025","title":"Large Language Models for Dysfluency Detection in Stuttered Speech","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2601.23255","title":"Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2604.19300","title":"HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models","created":"2026-04-21","cited_by_count":8,"area":null},{"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":"2410.15489","title":"Generative AI Agents in Autonomous Machines: A Safety Perspective","created":"2024-10-20","cited_by_count":7,"area":null},{"id":"2501.19377","title":"SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions","created":"2025-01-31","cited_by_count":7,"area":null},{"id":"2502.12900","title":"Soundwave: Less is More for Speech-Text Alignment in LLMs","created":"2025-02-18","cited_by_count":7,"area":null},{"id":"2506.08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2409.18680","title":"Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2410.13754","title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2410.15316","title":"Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2506.01111","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2510.12851","title":"Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering","created":"2025-10-14","cited_by_count":6,"area":null},{"id":"2310.10159","title":"Joint Music and Language Attention Models for Zero-shot Music Tagging","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2312.03632","title":"Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2403.14438","title":"A Multimodal Approach to Device-Directed Speech Detection with Large Language Models","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2406.09412","title":"Explore the Limits of Omni-modal Pretraining at Scale","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2409.06223","title":"Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models","created":"2024-09-10","cited_by_count":5,"area":null},{"id":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2506.09375","title":"CoLMbo: Speaker Language Model for Descriptive Profiling","created":"2025-06-11","cited_by_count":5,"area":null},{"id":"2601.04715","title":"On the Holistic Approach for Detecting Human Image Forgery","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2605.19833","title":"Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2506.01319","title":"Learning Sparsity for Effective and Efficient Music Performance Question Answering","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2506.08524","title":"Teaching Physical Awareness to LLMs through Sounds","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2509.04376","title":"AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anomaly Search","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2309.03884","title":"Zero-Shot Audio Captioning via Audibility Guidance","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2401.04935","title":"Learning Audio Concepts from Counterfactual Natural Language","created":"2024-01-10","cited_by_count":3,"area":null},{"id":"2409.01201","title":"EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2411.15685","title":"State-Space Large Audio Language Models","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2505.18517","title":"LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2506.00421","title":"Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2506.10423","title":"PAL: Probing Audio Encoders via LLMs -- Audio Information Transfer into LLMs","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2406.05876","title":"Zero-Shot End-To-End Spoken Question Answering In Medical Domain","created":"2024-06-09","cited_by_count":2,"area":null},{"id":"2406.18910","title":"Factor-Conditioned Speaking-Style Captioning","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2409.06635","title":"MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2409.08199","title":"AudioBERT: Audio Knowledge Augmented Language Model","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2409.09611","title":"Integrating Audio Narrations to Strengthen Domain Generalization in Multimodal First-Person Action Recognition","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2503.09205","title":"Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2503.16833","title":"The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2505.12524","title":"HAKES: Scalable Vector Database for Embedding Search Service","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2508.20976","title":"WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2509.00029","title":"From Sound to Sight: Towards AI-authored Music Videos","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2509.07526","title":"Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2509.20641","title":"Investigating Modality Contribution in Audio LLMs for Music","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2510.15231","title":"Extending Audio Context for Long-Form Understanding in Large Audio-Language Models","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2606.08194","title":"GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models","created":"2026-06-06","cited_by_count":2,"area":null},{"id":"2606.14141","title":"Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2609.00727","title":"Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2408.09269","title":"Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2409.01160","title":"Expanding on EnCLAP with Auxiliary Retrieval Model for Automated Audio Captioning","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2410.13268","title":"Roadmap towards Superhuman Speech Understanding using Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2412.01488","title":"TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2412.17306","title":"Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2502.05435","title":"Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2502.09645","title":"From No to Know: Taxonomy, Challenges, and Opportunities for Negation Understanding in Multimodal Foundation Models","created":"2025-02-10","cited_by_count":1,"area":null}],"next_cursor":"100"}