SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former
cs.SD, cs.AI, eess.AS
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/Luo-Zhengding/SAIL
Sources
- WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables
- Qwen2-Audio Technical Report
- STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
- SPUR: A Plug-and-Play Framework for Integrating Spatial Audio Understanding and Reasoning into Large Audio-Language Models
- PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMs
- SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios
- The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models
- NExT-GPT: Any-to-Any Multimodal LLM
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- The Llama 3 Herd of Models
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Qwen2.5-Omni Technical Report
- Step-Audio 2 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