{"total":63,"rows":[{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736,"area":"lr"},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560,"area":null},{"id":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530,"area":"mllm"},{"id":"2408.16725","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","created":"2024-08-29","cited_by_count":210,"area":"lr"},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"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":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"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":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2502.11946","title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","created":"2025-02-17","cited_by_count":83,"area":null},{"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":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"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":"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":"2409.17692","title":"MIO: A Foundation Model on Multimodal Tokens","created":"2024-09-26","cited_by_count":24,"area":null},{"id":"2412.12009","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","created":"2024-12-16","cited_by_count":21,"area":"inference"},{"id":"2411.03866","title":"Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward","created":"2024-11-06","cited_by_count":17,"area":null},{"id":"2502.13472","title":"FlexDuo: A Pluggable System for Enabling Full-Duplex Capabilities in Speech Dialogue Systems","created":"2025-02-19","cited_by_count":15,"area":null},{"id":"2412.16500","title":"Speech Retrieval-Augmented Generation without Automatic Speech Recognition","created":"2024-12-21","cited_by_count":14,"area":"rag"},{"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":"2407.14506","title":"On Pre-training of Multimodal Language Models Customized for Chart Understanding","created":"2024-07-19","cited_by_count":13,"area":"mllm"},{"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":"2505.13541","title":"SPIRIT: Patching Speech Language Models against Jailbreak Attacks","created":"2025-05-18","cited_by_count":9,"area":"safety"},{"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":"2409.19806","title":"PALM: Few-Shot Prompt Learning for Audio Language Models","created":"2024-09-29","cited_by_count":8,"area":"mllm"},{"id":"2601.20900","title":"Text-only adaptation in LLM-based ASR through text denoising","created":"2026-01-28","cited_by_count":8,"area":null},{"id":"2410.04819","title":"MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models","created":"2024-10-07","cited_by_count":7,"area":"mllm"},{"id":"2412.18072","title":"MMFactory: A Universal Solution Search Engine for Vision-Language Tasks","created":"2024-12-24","cited_by_count":7,"area":"mllm"},{"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":"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":"2410.15316","title":"Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2412.18566","title":"Zero-resource Speech Translation and Recognition with LLMs","created":"2024-12-24","cited_by_count":6,"area":null},{"id":"2506.11089","title":"Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM","created":"2025-06-05","cited_by_count":6,"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":"2604.00007","title":"Dynin-Omni: Omnimodal Unified Large Diffusion Language Model","created":"2026-03-09","cited_by_count":5,"area":"diffusion"},{"id":"2409.14526","title":"What Are They Doing? Joint Audio-Speech Co-Reasoning","created":"2024-09-22","cited_by_count":4,"area":"lr"},{"id":"2508.14130","title":"EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition","created":"2025-08-19","cited_by_count":4,"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":"2510.15851","title":"SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling","created":"2025-10-17","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":"2502.15264","title":"Retrieval-Augmented Speech Recognition Approach for Domain Challenges","created":"2025-02-21","cited_by_count":2,"area":"rag"},{"id":"2503.22711","title":"Modeling speech emotion with label variance and analyzing performance across speakers and unseen acoustic conditions","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2512.07571","title":"A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2601.20898","title":"Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection","created":"2026-01-28","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":"2410.13268","title":"Roadmap towards Superhuman Speech Understanding using Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2501.08421","title":"SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models","created":"2025-01-14","cited_by_count":1,"area":null},{"id":"2501.09104","title":"A Non-autoregressive Model for Joint STT and TTS","created":"2025-01-15","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":"2506.21864","title":"DeepOmni: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE","created":"2025-06-27","cited_by_count":1,"area":"mllm"},{"id":"2509.03526","title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2510.13906","title":"Switchboard-Affect: Emotion Perception Labels from Conversational Speech","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2602.09534","title":"AUHead: Realistic Emotional Talking Head Generation via Action Units Control","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2502.16137","title":"Chain-of-Description: What I can understand, I can put into words","created":"2025-02-22","cited_by_count":0,"area":"mllm"},{"id":"2508.19856","title":"TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.15692","title":"Direct Simultaneous Translation Activation for Large Audio-Language Models","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2510.19326","title":"Slot Filling as a Reasoning Task for SpeechLLMs","created":"2025-10-22","cited_by_count":0,"area":"lr"},{"id":"2602.18452","title":"RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity","created":"2026-02-04","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":"2606.14591","title":"AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models","created":"2026-06-12","cited_by_count":0,"area":"lr"},{"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}],"next_cursor":null}