{"total":92,"rows":[{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"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":"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":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"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":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17,"area":null},{"id":"2503.05085","title":"S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models","created":"2025-03-07","cited_by_count":16,"area":null},{"id":"2505.03054","title":"BLAB: Brutally Long Audio Bench","created":"2025-05-05","cited_by_count":11,"area":null},{"id":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","cited_by_count":11,"area":null},{"id":"2507.06256","title":"Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World","created":"2025-07-07","cited_by_count":9,"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":"2502.07608","title":"Time2Lang: Bridging Time-Series Foundation Models and Large Language Models for Health Sensing Beyond Prompting","created":"2025-02-11","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":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2512.10403","title":"BRACE: A Benchmark for Robust Audio Caption Quality Evaluation","created":"2025-12-11","cited_by_count":7,"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":"2508.12709","title":"MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning","created":"2025-08-18","cited_by_count":6,"area":null},{"id":"2601.12248","title":"AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering","created":"2026-01-18","cited_by_count":6,"area":null},{"id":"2603.09232","title":"How Contrastive Decoding Enhances Large Audio Language Models","created":"2026-03-10","cited_by_count":6,"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":"2506.09375","title":"CoLMbo: Speaker Language Model for Descriptive Profiling","created":"2025-06-11","cited_by_count":5,"area":null},{"id":"2509.18816","title":"Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Models","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2510.04584","title":"Robustness assessment of large audio language models in multiple-choice evaluation","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2504.08907","title":"Spatial Audio Processing with Large Language Model on Wearable Devices","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2509.18606","title":"FlexSED: Towards Open-Vocabulary Sound Event Detection","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2410.13114","title":"Sound Check: Auditing Audio Datasets","created":"2024-10-17","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":"2502.16794","title":"AAD-LLM: Neural Attention-Driven Auditory Scene Understanding","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2505.19294","title":"Towards Reliable Large Audio Language Model","created":"2025-05-25","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":"2601.23161","title":"DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2604.15383","title":"Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models","created":"2026-04-16","cited_by_count":3,"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":"2504.19327","title":"DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2508.00782","title":"SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation","created":"2025-08-01","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":"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":"2511.13273","title":"AudioMotionBench: Evaluating Auditory Motion Perception in Audio LLMs","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2512.09066","title":"ORCA: Open-ended Response Correctness Assessment for Audio Question Answering","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2601.11039","title":"SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models","created":"2026-01-16","cited_by_count":2,"area":null},{"id":"2602.14612","title":"Event-Grounded Question Answering over Long Audio via Structured Retrieval","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2603.16889","title":"Rubric-Guided Fine-tuning of SpeechLLMs for Multi-Aspect, Multi-Rater L2 Reading-Speech Assessment","created":"2026-02-28","cited_by_count":2,"area":null},{"id":"2603.19195","title":"How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2604.21926","title":"Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2606.05161","title":"Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2608.22236","title":"MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models","created":"2026-08-23","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":"2410.13268","title":"Roadmap towards Superhuman Speech Understanding using Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2412.20619","title":"Audiopedia: Audio QA with Knowledge","created":"2024-12-29","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},{"id":"2506.10312","title":"AC/DC: LLM-based Audio Comprehension via Dialogue Continuation","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2510.06223","title":"A Multimodal GUI Architecture for Interfacing with LLM-Based Conversational Assistants","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2601.12973","title":"Pardon? Evaluating Conversational Repair in Large Audio-Language Models","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2603.00355","title":"StethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical Tasks","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.14456","title":"PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmark","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2606.05177","title":"MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2606.09470","title":"A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language Rationales","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2608.29999","title":"TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2609.21183","title":"I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2410.03904","title":"Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2502.16584","title":"Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2506.07502","title":"DEBATE: A Dataset for Disentangling Textual Ambiguity in Mandarin Through Speech","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2509.10391","title":"Improving Audio Event Recognition with Consistency Regularization","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2510.04934","title":"AURA Score: A Metric For Holistic Audio Question Answering Evaluation","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2512.05994","title":"KidSpeak: A General Multi-purpose LLM for Kids' Speech Recognition and Screening","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2603.06542","title":"RAMoEA-QA: Hierarchical Specialization for Robust Respiratory Audio Question Answering","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.14343","title":"Localizing and Editing Knowledge in Large Audio-Language Models","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.25727","title":"Back to Basics: Revisiting ASR in the Age of Voice Agents","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2603.27667","title":"EvA: An Evidence-First Audio Understanding Paradigm for LALMs","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2604.23323","title":"Robust Audio-Text Retrieval via Cross-Modal Attention and Hybrid Loss","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2606.02739","title":"EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.23243","title":"Unlocking In-Context Learning in Audio-Language Models from Decentralized Medical Audio","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.02799","title":"Conversational Human Audio-visual Talking Dialogue Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.10299","title":"Empowering Long-form Omni-modal Understanding with Robust Audio Perception","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.17812","title":"ESCUCHA: A Spanish Speech Benchmark for Heterogeneous Acoustic Conditions","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.25314","title":"Sense it with your eyes: Sensation Generation and Understanding for Advertisements","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.02277","title":"Auditory Illusion Benchmark for Large Audio Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.12623","title":"SteerDuplex: Steerable Duplex Speech Dialogue Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.20195","title":"Music Hallucination in Audio-Language Models: A Hierarchical Formulation and Empirical Study","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.21666","title":"Samsone: A Family of Open Small Audio Language Models for On-Device Inference","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.22771","title":"ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech Understanding","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.30784","title":"Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33212","title":"CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34347","title":"SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.10663","title":"BEANS-Next and ROOTS: Broadening Audio-Language Capabilities for Bioacoustics","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.16942","title":"UA-Bench: Benchmarking Large Audio-Language Models on Underwater Acoustic Recognition","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}