{"total":220,"rows":[{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909,"area":"mllm"},{"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":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288,"area":"lr"},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197,"area":"mllm"},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"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":"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":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145,"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":"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":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"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":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"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":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67,"area":null},{"id":"2412.11102","title":"Empowering LLMs to Understand and Generate Complex Vector Graphics","created":"2024-12-15","cited_by_count":66,"area":null},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"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":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"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":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44,"area":null},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43,"area":"lr"},{"id":"2409.12319","title":"Large Language Models are Strong Audio-Visual Speech Recognition Learners","created":"2024-09-18","cited_by_count":42,"area":"mllm"},{"id":"2410.08565","title":"Baichuan-Omni Technical Report","created":"2024-10-11","cited_by_count":42,"area":null},{"id":"2503.20188","title":"Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector","created":"2025-03-26","cited_by_count":40,"area":"mllm"},{"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":"2412.08608","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":"2503.00413","title":"CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering","created":"2025-03-01","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":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2404.17858","title":"Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusion","created":"2024-04-27","cited_by_count":33,"area":"ssm"},{"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":"2504.01094","title":"Multilingual and Multi-Accent Jailbreaking of Audio LLMs","created":"2025-04-01","cited_by_count":31,"area":"safety"},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2406.02575","title":"Cross-Modal Safety Alignment: Is textual unlearning all you need?","created":"2024-05-27","cited_by_count":25,"area":"mllm"},{"id":"2406.02092","title":"MaskSR: Masked Language Model for Full-band Speech Restoration","created":"2024-06-04","cited_by_count":24,"area":null},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23,"area":null},{"id":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23,"area":null},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22,"area":null},{"id":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22,"area":null},{"id":"2310.04445","title":"LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model","created":"2023-10-02","cited_by_count":21,"area":null},{"id":"2505.15406","title":"Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models","created":"2025-05-21","cited_by_count":21,"area":"safety"},{"id":"2405.12107","title":"Imp: Highly Capable Large Multimodal Models for Mobile Devices","created":"2024-05-20","cited_by_count":20,"area":"mllm"},{"id":"2502.12425","title":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2025-02-18","cited_by_count":20,"area":"lr"},{"id":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2405.08317","title":"SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models","created":"2024-05-14","cited_by_count":18,"area":"mllm"},{"id":"2401.17851","title":"Instruction-Guided Scene Text Recognition","created":"2024-01-31","cited_by_count":17,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17,"area":null},{"id":"2309.04842","title":"Leveraging Large Language Models for Exploiting ASR Uncertainty","created":"2023-09-09","cited_by_count":15,"area":null},{"id":"2401.09774","title":"On the Audio Hallucinations in Large Audio-Video Language Models","created":"2024-01-18","cited_by_count":15,"area":null},{"id":"2406.03474","title":"AD-H: Language-guided Autonomous Driving with Hierarchical Agents","created":"2024-06-05","cited_by_count":15,"area":"driving"},{"id":"2308.10390","title":"LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models","created":"2023-08-20","cited_by_count":14,"area":null},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2402.12750","title":"Model Composition for Multimodal Large Language Models","created":"2024-02-20","cited_by_count":12,"area":"mllm"},{"id":"2409.09213","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","created":"2024-09-13","cited_by_count":12,"area":null},{"id":"2410.20178","title":"LLMs Can Evolve Continually on Modality for X-Modal Reasoning","created":"2024-10-26","cited_by_count":12,"area":"lr"},{"id":"2502.17812","title":"Can Multimodal LLMs Perform Time Series Anomaly Detection?","created":"2025-02-25","cited_by_count":12,"area":"mllm"},{"id":"2409.07841","title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models","created":"2024-09-12","cited_by_count":10,"area":null},{"id":"2505.13115","title":"Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning","created":"2025-05-19","cited_by_count":10,"area":"lr"},{"id":"2506.01307","title":"Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models","created":"2025-06-02","cited_by_count":9,"area":"mllm"},{"id":"2406.11025","title":"Large Language Models for Dysfluency Detection in Stuttered Speech","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2409.14993","title":"Multi-modal Generative AI: Multi-modal LLMs, Diffusions, and the Unification","created":"2024-09-23","cited_by_count":8,"area":"mllm"},{"id":"2409.19806","title":"PALM: Few-Shot Prompt Learning for Audio Language Models","created":"2024-09-29","cited_by_count":8,"area":"mllm"},{"id":"2412.09818","title":"MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models","created":"2024-12-13","cited_by_count":8,"area":"lr"},{"id":"2505.01199","title":"CaReAQA: A Cardiac and Respiratory Audio Question Answering Model for Open-Ended Diagnostic Reasoning","created":"2025-05-02","cited_by_count":8,"area":"lr"},{"id":"2601.23255","title":"Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2604.19300","title":"HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models","created":"2026-04-21","cited_by_count":8,"area":null},{"id":"2309.09843","title":"Instruction-Following Speech Recognition","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2406.09105","title":"INS-MMBench: A Comprehensive Benchmark for Evaluating LVLMs' Performance in Insurance","created":"2024-06-13","cited_by_count":7,"area":"mllm"},{"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":"2410.15489","title":"Generative AI Agents in Autonomous Machines: A Safety Perspective","created":"2024-10-20","cited_by_count":7,"area":null},{"id":"2501.19377","title":"SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions","created":"2025-01-31","cited_by_count":7,"area":null},{"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":"2506.08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2406.09617","title":"Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection","created":"2024-06-13","cited_by_count":6,"area":"mllm"},{"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":"2410.13754","title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","created":"2024-10-17","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":"2506.01111","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","created":"2025-06-01","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":"2510.12851","title":"Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering","created":"2025-10-14","cited_by_count":6,"area":null},{"id":"2511.20973","title":"Towards Audio Token Compression in Large Audio Language Models","created":"2025-11-26","cited_by_count":6,"area":"inference"},{"id":"2310.10159","title":"Joint Music and Language Attention Models for Zero-shot Music Tagging","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2312.03632","title":"Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2403.02905","title":"MMoFusion: Multi-modal Co-Speech Motion Generation with Diffusion Model","created":"2024-03-05","cited_by_count":5,"area":"diffusion"}],"next_cursor":"100"}