{"total":608,"rows":[{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120,"area":null},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"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":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497,"area":null},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455,"area":null},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288,"area":"lr"},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"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":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2503.12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","created":"2025-03-16","cited_by_count":182,"area":"lr"},{"id":"2505.18719","title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","created":"2025-05-24","cited_by_count":176,"area":"vla"},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174,"area":"moe"},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"area":null},{"id":"2406.11768","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","created":"2024-06-17","cited_by_count":156,"area":"lr"},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155,"area":"mllm"},{"id":"2505.16933","title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","created":"2025-05-22","cited_by_count":148,"area":"mllm"},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129,"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":"2407.04051","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","created":"2024-07-04","cited_by_count":122,"area":null},{"id":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121,"area":"lr"},{"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":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110,"area":"lr"},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109,"area":null},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2412.03104","title":"ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning","created":"2024-12-04","cited_by_count":103,"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":"2409.15272","title":"OmniBench: Towards The Future of Universal Omni-Language Models","created":"2024-09-23","cited_by_count":102,"area":"mllm"},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97,"area":"lr"},{"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":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88,"area":null},{"id":"2501.06282","title":"MinMo: A Multimodal Large Language Model for Seamless Voice Interaction","created":"2025-01-10","cited_by_count":79,"area":"mllm"},{"id":"2412.03556","title":"Best-of-N Jailbreaking","created":"2024-12-04","cited_by_count":76,"area":"safety"},{"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":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72,"area":"mllm"},{"id":"2410.18927","title":"SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models","created":"2024-10-24","cited_by_count":69,"area":"safety"},{"id":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68,"area":null},{"id":"2412.21037","title":"TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization","created":"2024-12-30","cited_by_count":68,"area":"diffusion"},{"id":"2502.17239","title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","created":"2025-02-24","cited_by_count":68,"area":null},{"id":"2501.09695","title":"Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key","created":"2025-01-16","cited_by_count":65,"area":"mllm"},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"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":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2408.01319","title":"A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Tasks","created":"2024-08-02","cited_by_count":57,"area":"mllm"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2410.09732","title":"LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models","created":"2024-10-13","cited_by_count":51,"area":"mllm"},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"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":"2504.08966","title":"PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models","created":"2025-04-11","cited_by_count":49,"area":"mllm"},{"id":"2412.09596","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","created":"2024-12-12","cited_by_count":48,"area":"mllm"},{"id":"2412.02611","title":"AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?","created":"2024-12-03","cited_by_count":47,"area":"mllm"},{"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":"2506.15220","title":"video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models","created":"2025-06-18","cited_by_count":47,"area":null},{"id":"2402.12786","title":"Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations","created":"2024-02-20","cited_by_count":45,"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":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44,"area":null},{"id":"2501.16566","title":"AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models","created":"2025-01-27","cited_by_count":44,"area":"mllm"},{"id":"2505.12929","title":"Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs","created":"2025-05-19","cited_by_count":44,"area":"lr"},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2410.08565","title":"Baichuan-Omni Technical Report","created":"2024-10-11","cited_by_count":42,"area":null},{"id":"2505.13237","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","created":"2025-05-19","cited_by_count":42,"area":"lr"},{"id":"2506.19835","title":"MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration","created":"2025-06-24","cited_by_count":40,"area":"lr"},{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39,"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":"2503.06073","title":"GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images","created":"2025-03-08","cited_by_count":39,"area":null},{"id":"2412.08608","title":"AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models","created":"2024-12-11","cited_by_count":38,"area":"safety"},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2410.23861","title":"Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models","created":"2024-10-31","cited_by_count":37,"area":"mllm"},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36,"area":"lr"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2505.15670","title":"SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","created":"2025-05-21","cited_by_count":34,"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":"2406.11427","title":"DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors","created":"2024-06-17","cited_by_count":32,"area":"diffusion"},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"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":"2409.10819","title":"EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer","created":"2024-09-17","cited_by_count":31,"area":"diffusion"},{"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":"2504.01094","title":"Multilingual and Multi-Accent Jailbreaking of Audio LLMs","created":"2025-04-01","cited_by_count":31,"area":"safety"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2402.14418","title":"Uncertainty-Aware Evaluation for Vision-Language Models","created":"2024-02-22","cited_by_count":29,"area":"mllm"},{"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":"2412.05679","title":"RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts","created":"2024-12-07","cited_by_count":29,"area":"mllm"},{"id":"2510.06590","title":"Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer","created":"2025-10-08","cited_by_count":28,"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":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2503.08540","title":"Mellow: a small audio language model for reasoning","created":"2025-03-11","cited_by_count":27,"area":"lr"},{"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":"2402.17954","title":"Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps","created":"2024-02-28","cited_by_count":25,"area":null},{"id":"2404.08856","title":"On Speculative Decoding for Multimodal Large Language Models","created":"2024-04-13","cited_by_count":25,"area":"mllm"},{"id":"2501.17202","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","created":"2025-01-27","cited_by_count":25,"area":null}],"next_cursor":"100"}