{"total":79,"rows":[{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736,"area":"lr"},{"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":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"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":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"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":"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":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2505.02625","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","created":"2025-05-05","cited_by_count":76,"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":"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":"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":"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":"2501.17202","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","created":"2025-01-27","cited_by_count":25,"area":null},{"id":"2501.13772","title":"Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models","created":"2025-01-23","cited_by_count":23,"area":"safety"},{"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":"2505.14103","title":"AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models","created":"2025-05-20","cited_by_count":18,"area":"safety"},{"id":"2510.12116","title":"Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2503.02769","title":"InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training","created":"2025-03-04","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":"2410.21485","title":"SpeechQE: Estimating the Quality of Direct Speech Translation","created":"2024-10-28","cited_by_count":10,"area":null},{"id":"2509.16589","title":"Benchmarking Contextual and Paralinguistic Reasoning in Speech-LLMs: A Case Study with In-the-Wild Data","created":"2025-09-20","cited_by_count":10,"area":"lr"},{"id":"2405.19041","title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","created":"2024-05-29","cited_by_count":9,"area":"synth"},{"id":"2502.19548","title":"When Large Language Models Meet Speech: A Survey on Integration Approaches","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2507.05177","title":"OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2412.15712","title":"Contrastive Learning for Task-Independent SpeechLLM-Pretraining","created":"2024-12-20","cited_by_count":8,"area":null},{"id":"2507.18452","title":"DIFFA: Large Language Diffusion Models Can Listen and Understand","created":"2025-07-24","cited_by_count":8,"area":"diffusion"},{"id":"2501.10937","title":"Leveraging Chain of Thought towards Empathetic Spoken Dialogue without Corresponding Question-Answering Data","created":"2025-01-19","cited_by_count":7,"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":"2410.17485","title":"VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning","created":"2024-10-23","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":"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":"2409.17044","title":"How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2410.03798","title":"Self-Powered LLM Modality Expansion for Large Speech-Text Models","created":"2024-10-04","cited_by_count":4,"area":null},{"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":"2505.17417","title":"Speechless: Speech Instruction Training Without Speech for Low Resource Languages","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2508.17863","title":"Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs","created":"2025-08-25","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":"2406.18088","title":"LLM-Driven Multimodal Opinion Expression Identification","created":"2024-06-26","cited_by_count":3,"area":null},{"id":"2411.08742","title":"A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models","created":"2024-11-13","cited_by_count":3,"area":null},{"id":"2505.18644","title":"Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving","created":"2025-05-24","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":"2601.06086","title":"AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning","created":"2025-12-31","cited_by_count":3,"area":"synth"},{"id":"2412.16771","title":"SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization","created":"2024-12-21","cited_by_count":2,"area":"lr"},{"id":"2503.10211","title":"Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2507.14815","title":"FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2507.18119","title":"GOAT-SLM: A Spoken Language Model with Paralinguistic and Speaker Characteristic Awareness","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2512.06380","title":"Protecting Bystander Privacy via Selective Hearing in Audio LLMs","created":"2025-12-06","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":"2410.13268","title":"Roadmap towards Superhuman Speech Understanding using Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2502.09284","title":"SparQLe: Speech Queries to Text Translation Through LLMs","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2506.06343","title":"TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2509.03526","title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2511.12077","title":"Learning to Hear by Seeing: It's Time for Vision Language Models to Understand Artistic Emotion from Sight and Sound","created":"2025-11-15","cited_by_count":1,"area":"mllm"},{"id":"2603.07025","title":"Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2606.09366","title":"Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs","created":"2026-06-08","cited_by_count":1,"area":"lr"},{"id":"2606.11033","title":"AuRA: Internalizing Audio Understanding into LLMs as LoRA","created":"2026-06-09","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":"2407.14875","title":"Seal: Advancing Speech Language Models to be Few-Shot Learners","created":"2024-07-20","cited_by_count":0,"area":null},{"id":"2504.08687","title":"Voice Interaction With Conversational AI Could Facilitate Thoughtful Reflection and Substantive Revision in Writing","created":"2025-04-11","cited_by_count":0,"area":"lr"},{"id":"2504.12339","title":"GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2602.10716","title":"RE-LLM: Refining Empathetic Speech-LLM Responses by Integrating Emotion Nuance","created":"2026-02-11","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":"2604.18159","title":"FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.12199","title":"Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.21453","title":"CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents","created":"2026-06-19","cited_by_count":0,"area":"agents"},{"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":"2608.18132","title":"Alignment Is All You Need: Instruction-Free Training for General Audio-Language Models","created":"2026-07-28","cited_by_count":0,"area":"mllm"},{"id":"2608.22908","title":"Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2610.06956","title":"EMODE: Dynamic Para-Semantic Experts for Emotion-Aware Speech Language Modeling","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.08085","title":"DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.11159","title":"Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15390","title":"From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.20253","title":"Repairing Speech Access After Text Updates with Frozen Affine Fields","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}