NVIDIA 或在 GTC 发布 Nemotron 3.5 Super VL 新模型
NVIDIA 预告下周 GTC 上可能发 Nemotron 3.5 Super VL，一个带视频理解的多模态模型，架构细节已经泄露出来了。
NVIDIA 预告下周推出新模型，时间点可能是 21 日周三的 GTC 大会。传闻中的候选是 Nemotron 3.5 Super VL，它采用 Nemotron-H 混合语言解码器搭配 RADIO 视觉编码器、视觉投影层和独立的时序视频嵌入器。该模型复用 Nemotron Omni 的图像/视频处理栈但去掉音频编码器，并保留共享的 Multi-Token Prediction（MTP）权重。
NVIDIA 🔥: A new model is set to arrive next week, possibly at the upcoming NVIDIA GTC event on Wednesday the 21st.
Are we getting the recently spotted Nemotron 3.5 Super VL, or something else on top of it?
> "Nemotron 3.5 Super VL combines a Nemotron-H hybrid language decoder with a RADIO vision encoder, a vision projector, and a separate temporal video embedder. It reuses the Nemotron Omni image/video stack without an audio encoder and retains shared Multi-Token Prediction (MTP) weights."
Monitoring 👀
