MOSS-VL Technical Report
- 类型：arxiv
- 标识：2608.15045
- 链接：https://arxiv.org/abs/2608.15045
- 主分类：multimodal
- 形态：method
- 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：We present MOSS-VL, an open vision-language model family that treats real-time interaction -- perceiving while it speaks -- as a first-class capability. It is co-designed across the stack: the language decoder attends to vision only through gated cross-attention, so the model can naturally see incoming frames while generating; a synthesized interaction corpus supervises when to speak, when to stay silent, and when to revise; and a staged curriculum concentrates all real-time-specific training in one light final stage over a strong offline foundation. Offline, MOSS-VL-Instruct is competitive at
- OpenAlex ID：W7203670747
- OpenAlex DOI：10.48550/arxiv.2608.15045
- DOI：10.48550/arxiv.2608.15045
- DOI来源：OpenAlex
- 开放获取：green
- 开放获取链接：https://doi.org/10.48550/arxiv.2608.15045
- OpenAlex更新：2026-08-23
- 待LLM分类：否
- 标题中文：MOSS-VL 技术报告
- TLDR中文：我们提出 MOSS-VL，一个开源视觉-语言模型系列，将实时交互（边说边看）视为一等能力。它贯穿整个栈进行协同设计：语言解码器仅通过门控交叉注意力访问视觉，因此模型在生成过程中可以自然地感知新输入帧；合成的交互语料用于监督何时说话、何时沉默、何时修正；分阶段课程将所有实时相关训练集中在一个轻量的最终阶段，基于强大的离线基础模型。在离线场景下，MOSS-VL-Instruct 在
- 来源文件：
- /inbox/tom/_candidates/2026-08-18-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]