RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark
cs.SD, cs.AI
Submitted: 2026-06-09
Updated: 2026-10-11
Terminology
Sources
- SALMONN: Towards Generic Hearing Abilities for Large Language Models
- Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
- Qwen2-Audio Technical Report
- Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities
- Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
- MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark
- MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
- SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models
- Qwen3-Omni Technical Report
- Qwen3.5-Omni Technical Report
- GPT-4o System Card
- Gemini: A Family of Highly Capable Multimodal Models
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- BLAB: Brutally Long Audio Bench
- AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs
- SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models
- STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
- Step-Audio 2 Technical Report
- DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding
- Step-Audio-R1 Technical Report
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