AnchorPrompt: Self-Distilled Soft Prompts for Robust Audio-Language Models

cs.SD, cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Project page: https://poonehmousavi.github.io/anchorprompt

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Qwen2-Audio Technical Report
• Qwen2.5-Omni Technical Report
• Kimi-Audio Technical Report
• Qwen3-Omni Technical Report
• Task-Aware Answer Preservation under Audio Compression for Large Audio Language Models
• Why Language Models Hallucinate
• EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillation

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