GigaChat Audio: Time-aware Large Audio Language Model
- 类型:arxiv
- 标识:2607.10387
- 链接:https://arxiv.org/abs/2607.10387
- 主分类:multimodal
- 形态:benchmark
- 被引:0
- 被引来源:Semantic Scholar + OpenAlex
- S2被引:0
- OpenAlex被引:0
- 影响力被引:0
- TLDR:This work presents a time-aware audio LLM that answers questions with explicit timestamps over up to 120 minutes of input using large-scale synthetic supervision from a cascaded pipeline and achieves strong temporal-grounding accuracy on short and long benchmarks.
- OpenAlex ID:W7168235853
- OpenAlex DOI:10.48550/arxiv.2607.10387
- DOI:10.48550/arxiv.2607.10387
- DOI来源:OpenAlex
- 开放获取:green
- 开放获取链接:https://doi.org/10.48550/arxiv.2607.10387
- OpenAlex更新:2026-08-24
- 待LLM分类:否
- 标题中文:GigaChat Audio:时间感知的大音频语言模型
- TLDR中文:本文提出一个时间感知的音频 LLM,能够基于大规模合成监督(来自级联 pipeline)在长达 120 分钟的输入上回答带有显式时间戳的问题,并在短时长和长时长 benchmark 上取得强劲的时间定位准确率。
- 来源文件:
- /inbox/tom/_candidates/2026-07-21-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]