Copertina

Locality Matters for Training-Free Audio Token Compression in Audio-Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Luo, Jiale, Liang, Xiaoyu, Hu, Haoji
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Towards Audio Token Compression in Large Audio Language Models
di: Bhati, Saurabhchand, et al.
Pubblicazione: (2025)

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models
di: He, Peize, et al.
Pubblicazione: (2026)

When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Models
di: Li, Chen-An, et al.
Pubblicazione: (2025)

From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training
di: Liu, Tianqiao, et al.
Pubblicazione: (2025)

Flatter Tokens are More Valuable for Speculative Draft Model Training
di: Fan, Jiaming, et al.
Pubblicazione: (2026)

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization
di: Wang, Dixuan, et al.
Pubblicazione: (2024)

Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study
di: Hou, Guanyu, et al.
Pubblicazione: (2025)

Causal Tracing of Audio-Text Fusion in Large Audio Language Models
di: Chen, Wei-Chih, et al.
Pubblicazione: (2026)

MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models
di: He, Yingxu, et al.
Pubblicazione: (2024)

IFEval-Audio: Benchmarking Instruction-Following Capability in Audio-based Large Language Models
di: Gao, Yiming, et al.
Pubblicazione: (2025)

Words at Play: Benchmarking Audio Pun Understanding in Large Audio-Language Models
di: Su, Yuchen, et al.
Pubblicazione: (2026)

SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia
di: Liu, Chaoqun, et al.
Pubblicazione: (2025)

AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
di: Li, Kai, et al.
Pubblicazione: (2025)

ALARM: Audio-Language Alignment for Reasoning Models
di: Grinberg, Petr, et al.
Pubblicazione: (2026)

MiMo-Audio: Audio Language Models are Few-Shot Learners
di: Core Team, et al.
Pubblicazione: (2025)

On the Audio Hallucinations in Large Audio-Video Language Models
di: Nishimura, Taichi, et al.
Pubblicazione: (2024)

Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
di: Feng, Bo-Han, et al.
Pubblicazione: (2026)

AudioBERT: Audio Knowledge Augmented Language Model
di: Ok, Hyunjong, et al.
Pubblicazione: (2024)

AHELM: A Holistic Evaluation of Audio-Language Models
di: Lee, Tony, et al.
Pubblicazione: (2025)

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
di: Fang, Zheng, et al.
Pubblicazione: (2026)

Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models
di: Xiong, Zhen, et al.
Pubblicazione: (2025)

SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models
di: Sun, Yirong, et al.
Pubblicazione: (2026)

AudioBench: A Universal Benchmark for Audio Large Language Models
di: Wang, Bin, et al.
Pubblicazione: (2024)

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
di: Wang, Cheng, et al.
Pubblicazione: (2025)

VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
di: Long, Zuwei, et al.
Pubblicazione: (2025)

Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models
di: Ieong, Lok-Lam, et al.
Pubblicazione: (2026)

From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical Prediction
di: Zhu, Mingcheng, et al.
Pubblicazione: (2026)

Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models
di: Chen, Yiming, et al.
Pubblicazione: (2024)

Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Models
di: Wang, Junyu, et al.
Pubblicazione: (2025)

Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
di: Ghosh, Sreyan, et al.
Pubblicazione: (2025)

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
di: Goel, Arushi, et al.
Pubblicazione: (2025)

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
di: Huang, Ailin, et al.
Pubblicazione: (2025)

Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models
di: Sridhar, Arvind Krishna, et al.
Pubblicazione: (2024)

Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding
di: Hsu, Tzu-wen, et al.
Pubblicazione: (2025)

Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
di: Ye, Zhen, et al.
Pubblicazione: (2024)

Dynamic Token Reduction during Generation for Vision Language Models
di: Liang, Xiaoyu, et al.
Pubblicazione: (2025)

Pardon? Evaluating Conversational Repair in Large Audio-Language Models
di: Huang, Shuanghong, et al.
Pubblicazione: (2026)

Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model
di: Ma, Ziyang, et al.
Pubblicazione: (2025)

Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding
di: Liu, Jizhong, et al.
Pubblicazione: (2024)

Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and Beyond
di: Han, Soyeon Caren, et al.
Pubblicazione: (2024)