{"total":85,"rows":[{"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":"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":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"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":"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":"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":"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":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"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":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108,"area":"mllm"},{"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":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"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":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2502.17810","title":"URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models","created":"2025-02-25","cited_by_count":30,"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":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26,"area":"moe"},{"id":"2506.07233","title":"Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding","created":"2025-06-08","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":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2502.06710","title":"Learning Musical Representations for Music Performance Question Answering","created":"2025-02-10","cited_by_count":17,"area":null},{"id":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"area":null},{"id":"2305.17993","title":"Multi-Scale Attention for Audio Question Answering","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2506.20960","title":"OmniEval: A Benchmark for Evaluating Omni-modal Models with Visual, Auditory, and Textual Inputs","created":"2025-06-26","cited_by_count":13,"area":null},{"id":"2508.15407","title":"When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models","created":"2025-08-21","cited_by_count":13,"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":"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":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2311.09363","title":"Investigating the Emergent Audio Classification Ability of ASR Foundation Models","created":"2023-11-15","cited_by_count":10,"area":null},{"id":"2504.09897","title":"TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models","created":"2025-04-14","cited_by_count":9,"area":"mllm"},{"id":"2505.07609","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2407.20454","title":"CoMMIT: Coordinated Multimodal Instruction Tuning","created":"2024-07-29","cited_by_count":8,"area":"mllm"},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2406.09833","title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","created":"2024-06-14","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":"2505.22765","title":"StressTest: Can YOUR Speech LM Handle the Stress?","created":"2025-05-28","cited_by_count":7,"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":"2512.05745","title":"ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior","created":"2025-12-05","cited_by_count":7,"area":"mllm"},{"id":"2601.19956","title":"VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2602.00846","title":"Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis","created":"2026-01-31","cited_by_count":7,"area":"mllm"},{"id":"2412.13050","title":"Modality-Inconsistent Continual Learning of Multimodal Large Language Models","created":"2024-12-17","cited_by_count":6,"area":"mllm"},{"id":"2503.07663","title":"Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs","created":"2025-03-08","cited_by_count":6,"area":"mllm"},{"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":"2406.09412","title":"Explore the Limits of Omni-modal Pretraining at Scale","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2505.17110","title":"Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling","created":"2025-05-21","cited_by_count":5,"area":"mllm"},{"id":"2506.07575","title":"Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models","created":"2025-06-09","cited_by_count":5,"area":"mllm"},{"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":"2312.17343","title":"AQUALLM: Audio Question Answering Data Generation Using Large Language Models","created":"2023-12-28","cited_by_count":4,"area":null},{"id":"2410.12109","title":"OMCAT: Omni Context Aware Transformer","created":"2024-10-15","cited_by_count":4,"area":"mllm"},{"id":"2506.01319","title":"Learning Sparsity for Effective and Efficient Music Performance Question Answering","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2510.13558","title":"Steer-MoE: Efficient Audio-Language Alignment with a Mixture-of-Experts Steering Module","created":"2025-10-15","cited_by_count":3,"area":"moe"},{"id":"2603.09853","title":"SCENEBench: An Audio Understanding Benchmark Grounded in Assistive and Industrial Use Cases","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2604.15383","title":"Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2305.19769","title":"Attention-Based Methods For Audio Question Answering","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2406.05876","title":"Zero-Shot End-To-End Spoken Question Answering In Medical Domain","created":"2024-06-09","cited_by_count":2,"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":"2605.00969","title":"MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio","created":"2026-05-01","cited_by_count":2,"area":"lr"},{"id":"2412.20619","title":"Audiopedia: Audio QA with Knowledge","created":"2024-12-29","cited_by_count":1,"area":null},{"id":"2506.10312","title":"AC/DC: LLM-based Audio Comprehension via Dialogue Continuation","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2509.21960","title":"Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2511.15552","title":"Multimodal Evaluation of Russian-language Architectures","created":"2025-11-19","cited_by_count":1,"area":"mllm"},{"id":"2601.12973","title":"Pardon? Evaluating Conversational Repair in Large Audio-Language Models","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2604.21766","title":"AUDITA: A New Dataset to Audit Humans vs. AI Skill at Audio QA","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2607.00247","title":"Adaptive Perturbation Selection for Contrastive Audio Decoding","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.05365","title":"SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2609.07286","title":"TAD: Token-Adaptive Contrastive Decoding with Confidence-Guided Gating for Hallucination Mitigation in Large Audio-Language Models","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2406.09156","title":"Towards Multilingual Audio-Visual Question Answering","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2503.15338","title":"Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2507.06329","title":"MixAssist: An Audio-Language Dataset for Co-Creative AI Assistance in Music Mixing","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2510.04934","title":"AURA Score: A Metric For Holistic Audio Question Answering Evaluation","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2604.16502","title":"Topology-Aware Layer Pruning for Large Vision-Language Models","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2606.02739","title":"EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.04619","title":"CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.23758","title":"EXAM2: Extending Audio Understanding in Multilingual and Multimodal Analysis","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.02343","title":"SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.12437","title":"Beyond the Query: Do Retrieval Signals Improve Adaptive Multimodal RAG Routing?","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.21666","title":"Samsone: A Family of Open Small Audio Language Models for On-Device Inference","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.30784","title":"Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language Models","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}