{"total":101,"rows":[{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"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":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200,"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":"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":"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":"2503.04721","title":"Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities","created":"2025-03-06","cited_by_count":100,"area":null},{"id":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82,"area":"mllm"},{"id":"2501.07246","title":"Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model","created":"2025-01-13","cited_by_count":62,"area":"lr"},{"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":"2503.01174","title":"Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics","created":"2025-03-03","cited_by_count":47,"area":null},{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"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":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40,"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":"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":"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":"2412.05167","title":"Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models","created":"2024-12-06","cited_by_count":29,"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":"2409.18142","title":"A Survey on Multimodal Benchmarks: In the Era of Large AI Models","created":"2024-09-21","cited_by_count":27,"area":"mllm"},{"id":"2505.19037","title":"Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models","created":"2025-05-25","cited_by_count":27,"area":null},{"id":"2409.07437","title":"Salmon: A Suite for Acoustic Language Model Evaluation","created":"2024-09-11","cited_by_count":24,"area":null},{"id":"2506.07233","title":"Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding","created":"2025-06-08","cited_by_count":24,"area":null},{"id":"2411.07111","title":"Building a Taiwanese Mandarin Spoken Language Model: A First Attempt","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2406.19954","title":"BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5","created":"2024-06-28","cited_by_count":19,"area":null},{"id":"2505.15727","title":"VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models","created":"2025-05-21","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":"2504.09081","title":"SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning","created":"2025-04-12","cited_by_count":14,"area":null},{"id":"2401.00273","title":"Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision","created":"2023-12-30","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":"2409.16644","title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2408.13040","title":"SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks","created":"2024-08-23","cited_by_count":12,"area":null},{"id":"2505.03054","title":"BLAB: Brutally Long Audio Bench","created":"2025-05-05","cited_by_count":11,"area":null},{"id":"2505.14518","title":"Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples","created":"2025-05-20","cited_by_count":11,"area":null},{"id":"2505.17496","title":"Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2510.22758","title":"EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models","created":"2025-10-26","cited_by_count":11,"area":null},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2410.12948","title":"What Do Speech Foundation Models Not Learn About Speech?","created":"2024-10-16","cited_by_count":8,"area":null},{"id":"2604.24401","title":"All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation","created":"2026-04-27","cited_by_count":8,"area":"lr"},{"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":"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":"2408.13891","title":"SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning","created":"2024-08-25","cited_by_count":6,"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":"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":"2510.00628","title":"Hearing the Order: Investigating Position Bias in Large Audio-Language Models","created":"2025-10-01","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":"2602.11488","title":"When Audio-LLMs Don't Listen: A Cross-Linguistic Study of Modality Arbitration","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2602.17598","title":"The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\\rightarrow$LLM Pipelines?","created":"2026-02-19","cited_by_count":5,"area":null},{"id":"2603.13768","title":"Causal Tracing of Audio-Text Fusion in Large Audio Language Models","created":"2026-03-14","cited_by_count":5,"area":null},{"id":"2605.15104","title":"From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents","created":"2026-05-14","cited_by_count":5,"area":"agents"},{"id":"2409.02384","title":"STAB: Speech Tokenizer Assessment Benchmark","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2409.14526","title":"What Are They Doing? Joint Audio-Speech Co-Reasoning","created":"2024-09-22","cited_by_count":4,"area":"lr"},{"id":"2505.13338","title":"Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2508.07273","title":"Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models","created":"2025-08-10","cited_by_count":4,"area":null},{"id":"2510.16893","title":"Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations","created":"2025-10-19","cited_by_count":4,"area":null},{"id":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2501.06562","title":"Discrete Speech Unit Extraction via Independent Component Analysis","created":"2025-01-11","cited_by_count":3,"area":null},{"id":"2504.15509","title":"SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2508.15418","title":"LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2604.10065","title":"ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2407.04482","title":"Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2503.16718","title":"CAARMA: Class Augmentation with Adversarial Mixup Regularization","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2507.19361","title":"SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models","created":"2025-07-25","cited_by_count":2,"area":"agents"},{"id":"2509.22461","title":"CMDAR: A Chinese Multi-scene Dynamic Audio Reasoning Benchmark with Diverse Challenges","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2512.06380","title":"Protecting Bystander Privacy via Selective Hearing in Audio LLMs","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2606.23052","title":"CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models","created":"2026-06-22","cited_by_count":2,"area":"distill"},{"id":"2608.19515","title":"Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does","created":"2026-08-20","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":"2509.26329","title":"TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.17662","title":"DELULU: Discriminative Embedding Learning Using Latent Units for Speaker-Aware Self-Trained Speech Foundational Model","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2601.00777","title":"Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detection","created":"2026-01-02","cited_by_count":1,"area":"mllm"},{"id":"2601.06106","title":"Judge Model for Large-scale Multimodality Benchmarks","created":"2026-01-03","cited_by_count":1,"area":null},{"id":"2603.18048","title":"DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models","created":"2026-03-17","cited_by_count":1,"area":"mllm"},{"id":"2605.14607","title":"ViMU: Benchmarking Video Metaphorical Understanding","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.30899","title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.01016","title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2607.12290","title":"The Sound of Absence: Audio-Language Embedding Models Struggle with Negation","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2608.06409","title":"Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.06718","title":"Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.08772","title":"Multilingual Emotion Neurons in Large Audio-Language Models","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2608.09189","title":"EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.00570","title":"VoiceLongMemEval: Do Assistants Remember How You Sounded?","created":"2026-09-01","cited_by_count":1,"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":"2503.15338","title":"Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2506.07294","title":"Towards Generalized Source Tracing for Codec-Based Deepfake Speech","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2509.08031","title":"AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.18200","title":"Conversational Orientation Reasoning: Egocentric-to-Allocentric Navigation with Multimodal Chain-of-Thought","created":"2025-09-20","cited_by_count":0,"area":"lr"},{"id":"2605.04556","title":"Benchmarking LLMs on the Massive Sound Embedding Benchmark (MSEB)","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2607.10162","title":"Hearing Like Humans? Sound Symbolism and Perceptual Alignment in Speech Language Models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.11801","title":"Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Models","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.13408","title":"Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models","created":"2026-07-15","cited_by_count":0,"area":"alignment"},{"id":"2607.17812","title":"ESCUCHA: A Spanish Speech Benchmark for Heterogeneous Acoustic Conditions","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.17102","title":"Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.23758","title":"EXAM2: Extending Audio Understanding in Multilingual and Multimodal Analysis","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.26317","title":"Modality Maturity Index: A benchmark for assessing multimodal capabilities of omni models","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.27176","title":"When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2608.27817","title":"Auditing generative audio calls for known-task audio-llm evaluation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.40198","title":"SCB: SpeechConversationBench for Evaluating Multi-Turn Reasoning in Speech-to-Speech Models","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}