AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models
cs.SD, cs.LG
Submitted: 2026-10-03
Updated: 2026-10-03
Terminology
Sources
- MiMo-Audio: Audio Language Models are Few-Shot Learners
- Kimi-Audio Technical Report
- SALMONN: Towards Generic Hearing Abilities for Large Language Models
- Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
- SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities
- AudioBench: A Universal Benchmark for Audio Large Language Models
- MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark
- ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models
- NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation
- VoxSafeBench: Not Just What Is Said, but Who, How, and Where
- VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models
- EvoAudio: Recursive Self-Improvement for Audio Understanding
- Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
- SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning
- Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning
- Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning
- AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
- Self-Improvement for Audio Large Language Model using Unlabeled Speech
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs