From 9bb9169ec81100b7a41985f080ad5591f3ef0639 Mon Sep 17 00:00:00 2001 From: Nabin Mulepati Date: Tue, 28 Apr 2026 10:14:56 -0600 Subject: [PATCH] add links back to announcement pages --- docs/devnotes/posts/vlm-long-document-understanding.md | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/docs/devnotes/posts/vlm-long-document-understanding.md b/docs/devnotes/posts/vlm-long-document-understanding.md index 874644bd8..791bd04af 100644 --- a/docs/devnotes/posts/vlm-long-document-understanding.md +++ b/docs/devnotes/posts/vlm-long-document-understanding.md @@ -596,7 +596,9 @@ The recipes below are the self-contained, runnable scripts for each stage of the Key Resources: 1. [NeMo Data Designer on GitHub](https://github.com/NVIDIA-NeMo/DataDesigner) -2. [MMLongBench-Doc Benchmark](https://mayahq.github.io/MMLongBench-Doc/) -3. [Nemotron-3-Nano-Omni technical report](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Omni-report.pdf) -4. [Nemotron-3-Nano-Omni HF Model page](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16) -5. [Qwen3-VL Model Family](https://huggingface.co/Qwen) +2. [Nemotron-3-Nano-Omni technical report](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Omni-report.pdf) +3. [NVIDIA Tech post announcing Nemotron-3-Nano-Omni](https://developer.nvidia.com/blog/nvidia-nemotron-3-nano-omni-powers-multimodal-agent-reasoning-in-a-single-efficient-open-model) +4. [Hugging Face post introducing Nemotron-3-Nano-Omni](https://huggingface.co/blog/nvidia/nemotron-3-nano-omni-multimodal-intelligence) +5. [Nemotron-3-Nano-Omni HF Model page](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16) +6. [MMLongBench-Doc Benchmark](https://arxiv.org/abs/2407.01523) +7. [Qwen3-VL Model Family](https://huggingface.co/Qwen)