{"total":68,"rows":[{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2512.23808","title":"MiMo-Audio: Audio Language Models are Few-Shot Learners","created":"2025-12-29","cited_by_count":65,"area":null},{"id":"2503.14324","title":"DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies","created":"2025-03-18","cited_by_count":42,"area":null},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2505.03739","title":"VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model","created":"2025-05-06","cited_by_count":31,"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":"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":"2507.15375","title":"STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models","created":"2025-07-21","cited_by_count":26,"area":"lr"},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26,"area":"moe"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2506.23325","title":"XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs","created":"2025-06-29","cited_by_count":23,"area":null},{"id":"2511.10262","title":"MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models","created":"2025-11-13","cited_by_count":22,"area":null},{"id":"2510.06917","title":"SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models","created":"2025-10-08","cited_by_count":19,"area":"lr"},{"id":"2512.20156","title":"Fun-Audio-Chat Technical Report","created":"2025-12-23","cited_by_count":19,"area":null},{"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":"2511.05516","title":"Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation","created":"2025-10-26","cited_by_count":17,"area":null},{"id":"2507.05727","title":"ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark","created":"2025-07-08","cited_by_count":15,"area":null},{"id":"2603.18090","title":"MOSS-TTS Technical Report","created":"2026-03-18","cited_by_count":14,"area":null},{"id":"2506.21875","title":"WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wild","created":"2025-06-27","cited_by_count":13,"area":"mllm"},{"id":"2508.16790","title":"TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling","created":"2025-08-22","cited_by_count":13,"area":null},{"id":"2604.12928","title":"MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models","created":"2026-04-14","cited_by_count":12,"area":null},{"id":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","cited_by_count":11,"area":null},{"id":"2509.09716","title":"VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions","created":"2025-09-09","cited_by_count":9,"area":null},{"id":"2508.20916","title":"SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement","created":"2025-08-28","cited_by_count":7,"area":null},{"id":"2602.09823","title":"Covo-Audio Technical Report","created":"2026-02-10","cited_by_count":7,"area":null},{"id":"2605.23912","title":"Raon-Speech Technical Report","created":"2026-04-08","cited_by_count":7,"area":null},{"id":"2512.10324","title":"EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs","created":"2025-12-11","cited_by_count":6,"area":"inference"},{"id":"2603.17837","title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2506.23049","title":"AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks","created":"2025-06-29","cited_by_count":5,"area":"lr"},{"id":"2508.11818","title":"Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understanding","created":"2025-08-15","cited_by_count":5,"area":"lr"},{"id":"2510.16756","title":"End-to-end Listen, Look, Speak and Act","created":"2025-10-19","cited_by_count":5,"area":"moe"},{"id":"2510.11098","title":"VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents","created":"2025-10-13","cited_by_count":4,"area":"agents"},{"id":"2510.26096","title":"ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models","created":"2025-10-30","cited_by_count":4,"area":"safety"},{"id":"2604.06871","title":"Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2505.14438","title":"S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2509.20072","title":"From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","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":"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":"2509.03940","title":"VoxRole: A Comprehensive Benchmark for Evaluating Speech-Based Role-Playing Agents","created":"2025-09-04","cited_by_count":2,"area":"agents"},{"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":"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":"2602.06602","title":"Scaling Speech Tokenizers with Diffusion Autoencoders","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2607.16107","title":"Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos","created":"2026-07-17","cited_by_count":2,"area":"lr"},{"id":"2505.13181","title":"Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2506.12537","title":"What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2506.21864","title":"DeepOmni: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE","created":"2025-06-27","cited_by_count":1,"area":"mllm"},{"id":"2508.01178","title":"Advancing the Foundation Model for Music Understanding","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2601.07274","title":"Towards Comprehensive Semantic Speech Embeddings for Chinese Dialects","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2602.04913","title":"A$^2$-LLM: An End-to-end Conversational Audio Avatar Large Language Model","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.24080","title":"Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.22267","title":"TiCo: Time-Controllable Spoken Dialogue Model","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2605.06765","title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","created":"2026-05-07","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":"2609.25176","title":"Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction","created":"2026-09-21","cited_by_count":1,"area":"agents"},{"id":"2609.34247","title":"SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2508.07964","title":"Toward Machine Interpreting: Lessons from Human Interpreting Studies","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2508.10015","title":"RealTalk-CN: A Realistic Chinese Speech-Text Dialogue Benchmark With Cross-Modal Interaction Analysis","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2601.16540","title":"Do Models Hear Like Us? Probing the Representational Alignment of Audio LLMs and Naturalistic EEG","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2603.09215","title":"SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models","created":"2026-03-10","cited_by_count":0,"area":"inference"},{"id":"2605.10199","title":"How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.27984","title":"KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMs","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2605.31521","title":"UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.19932","title":"Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2609.12563","title":"TokenMapper: A Step Toward Interoperable Speech Token Translation","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.15313","title":"Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy Distillation","created":"2026-09-14","cited_by_count":0,"area":"distill"},{"id":"2609.26488","title":"Spoken Language Models that Think Aloud","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2610.12214","title":"DiffuPlex: Accelerating Full-Duplex Spoken Dialog Models via Rolling Masked Diffusion","created":"2026-10-08","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}