ReListen: Training-Free Evidence Localization in Hour-Long Audio with Frozen Audio Language Models
cs.CL, cs.SD, eess.AS
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- BLAB: Brutally Long Audio Bench
- Qwen2-Audio Technical Report
- AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs
- Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR
- ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models
- Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding
- Qwen3-Omni Technical Report
- Qwen2.5-Omni Technical Report
- VoiceGiraffe: A Benchmark for Extreme Long-Context Audio-Language Understanding
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data