Event ·Multi-source

NVIDIA 发布 Nemotron 3.5 Super VL：单一模型整合文本与视觉理解

NVIDIA 发布 Nemotron 3.5 Super VL，把文本理解和视觉理解合并到一个模型中。智能体在执行任务时需要读取文档、解读图表、搜索网页，此前要在独立的文本模型和视觉模型之间传递上下文。该模型减少了这种跨模型传上下文的做法，让智能体在一个模型内完成多模态任务。

Current read

NVIDIA 出了个 Nemotron 3.5 Super VL，文本和图像看图一个模型全包，做智能体不用再在两个模型之间倒腾上下文了。

11 sources51° AI heatLast updated 2026/10/15 15:09:11

Evidence

11 sources

Primary sourceNVIDIA AI

2026/10/15 15:09:11View source

Related source 1OpenRouter

2026/10/15 15:30:15View source

Related source 2TestingCatalog

2026/10/16 07:05:02View source

Related source 3Together AI

2026/10/15 15:01:33View source

Related source 4vLLM

2026/10/15 15:50:21View source

Related source 5Decoder

2026/10/15 16:09:44View source

Related source 6marktechpost

2026/10/15 19:53:50View source

Related source 7ollama

2026/10/15 23:50:31View source

Related source 8Scale AI

2026/10/15 15:12:57View source

Related source 9LangChain

2026/10/15 15:17:36View source

Related source 10Artificial Analysis

2026/10/15 15:51:19View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story