EvoAudio: Recursive Self-Improvement for Audio Understanding
cs.SD, cs.LG
Submitted: 2026-09-23
Updated: 2026-09-23
Project page: https://jensenyx.github.io/EvoAudio.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MiMo-Audio: Audio Language Models are Few-Shot Learners
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Kimi-Audio Technical Report
- Qwen3-TTS Technical Report
- VoxSafeBench: Not Just What Is Said, but Who, How, and Where
- VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
- SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning
- Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning
- AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
- MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
- Self-Improvement for Audio Large Language Model using Unlabeled Speech
- Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning
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