AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs
Shanghai Jiao Tong University(上海交通大学);Shanghai AI Laboratory(上海人工智能实验室);Northeastern University(东北大学);Carnegie Mellon University(卡内基梅隆大学);University of Chinese Academy of Sciences(中国科学院大学);Tsinghua University(清华大学);Sun Yat-sen University(中山大学)
Processing long-form audio is a major challenge for Large Audio Language models (LALMs). These models struggle with the quadratic cost of attention ($O(N^2)$) and with modeling long-range temporal dependencies. Existing audio benchmarks are built mostly from short clips and do not evaluate models in realistic long context settings. To address this gap, we introduce AudioMarathon, a benchmark designed to evaluate both understanding and inference efficiency on long-form audio. AudioMarathon provides a diverse set of tasks built upon three pillars: long-context audio inputs with durations ranging from 90.0 to 300.0 seconds, which correspond to encoded sequences of 2,250 to 7,500 audio tokens, respectively, full domain coverage across speech, sound, and music, and complex reasoning that requires multi-hop inference. We evaluate state-of-the-art LALMs and observe clear performance drops as audio length grows. We also study acceleration techniques and analyze the trade-offs of token pruning and KV cache eviction. The results show large gaps across current LALMs and highlight the need for better temporal reasoning and memory-efficient architectures. We believe AudioMarathon will drive the audio and multimodal research community to develop more advanced audio understanding models capable of solving complex audio tasks.
HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models
EPIC Lab, Shanghai Jiao Tong University(上海交通大学EPIC实验室);DAIL Tech(DAIL科技);Northeastern University(东北大学);Sichuan University(四川大学);Huazhong University of Science and Technology(华中科技大学)
PAL: Probing Audio Encoders via LLMs -- Audio Information Transfer into LLMs
Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK(视觉、语音和信号处理中心(CVSSP),英国萨里大学);Surrey Institute for People-Centred AI, University of Surrey, Guildford, GU2 7XH, UK(萨里大学以人为中心的人工智能研究所,英国Guildford);Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE(穆罕默德·本·扎耶德人工智能大学(MBZUAI),阿布扎赫德)
Speech-XL: Towards Long-Form Speech Understanding in Large Speech Language Models
TMCC, College of Computer Science, Nankai University, Tianjin, China(TMCC,计算机科学学院,南开大学,天津,中国);Alibaba International Digital Commerce(阿里巴巴国际数字商业);University of Exeter, Exeter, United Kingdom(埃克塞特大学,埃克塞特,英国)
Do Models Hear Like Us? Probing the Representational Alignment of Audio LLMs and Naturalistic EEG
School of Computer Science, Chongqing University(重庆大学计算机科学学院);Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua University(清华大学计算机科学与技术系、人工智能研究院);School of Economics and Business Administration, Chongqing University(重庆大学经济与商业管理学院);School of Artificial Intelligence, Southwest University(西南大学人工智能学院);The First Affiliated Hospital of Chongqing Medical University(重庆医科大学第一附属医院)
Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation
Columbia University(哥伦比亚大学);University of Washington(华盛顿大学)
Protecting Bystander Privacy via Selective Hearing in Audio LLMs
VRAIN, Universitat Politècnica de València(VRAIN,瓦伦西亚理工大学);Department of Engineering, University of Cambridge(剑桥大学工程系);INGENIO (CSIC-Universitat Politècnica de València)(INGENIO(CSIC-瓦伦西亚理工大学))
Evaluating Hallucinations in Audio-Visual Multimodal LLMs with Spoken Queries under Diverse Acoustic Conditions
Department of Intelligent Software, Sungkyunkwan University(智能软件系,成均馆大学);Department of Computer Science and Engineering, Sungkyunkwan University(计算机科学与工程系,成均馆大学)
SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former
Nanyang Technological University(南洋理工大学);Singapore Management University(新加坡管理大学);Tencent Hy Frontier Lab(腾讯Hy前沿实验室);Beijing Institute of Technology(北京理工大学);University of Surrey(萨里大学)
Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detection
State Key Laboratory of Media Convergence and Communication(媒体融合与传播国家重点实验室);Communication University of China(中国传媒大学);Machine Intelligence(人工智能);Key Laboratory of Media Audio & Video, Ministry of Education, Communication University of China(教育部媒体音频视频重点实验室)
From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
Surrey Institute for People-Centred AI (PAI)(萨里人本人工智能研究所);University of Surrey(萨里大学);Centre for Vision, Speech and Signal Processing (CVSSP)(视觉、语音和信号处理中心)
Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought
Tianjin Key Laboratory of Cognitive Computing(天津认知计算实验室);Tianjin University(天津大学);Huiyan Technology Company, Ltd.(慧颜科技有限公司);Chinese Academy of Sciences(中国科学院);Tencent(腾讯)
Probing Cross-modal Information Hubs in Audio-Visual LLMs
Department of Electrical Engineering, Korea Advanced Institute of Science;The Graduate School of Advanced Imaging Science, Multimedia \& Film, Chung-Ang University, Seoul, Republic of Korea
MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders
Institute for Infocomm Research (I 2 2 {}^{\text{2}} start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPT R)(信息与通信研究 institute);Agency for Science, Technology and Research (A*STAR)(科技研究局);Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR)(前沿人工智能研究 center)