Nemotron 3.5 Embed froze language towers, so existing text vectors survive the vision upgrade
tomaarsen · x · 2026-10-22
tomaarsen highlights a practical design choice in Nemotron 3.5 Embed: NVIDIA kept the language towers frozen while training the vision components, preserving the text embedding spaces. Users already doing text retrieval with Nemotron 3 Embed can reuse existing text vectors and add image retrieval without re-embedding.
Related event: NVIDIA Open-Sources Nemotron 3.5 Retriever Suite: Embed, Rerank, Parse(12 posts)→
More from Models
- Grok Bot now live in X Chat, handling calendars and inbox — elonmusk · 2026-10-23
- AI2's OlmoEarth embeddings beat AlphaEarth and Tessera v2 on 10 of 11 evals — allen_ai · 2026-10-22
- Developer attempts to burn through a week of Codex usage in just 4 hours — jasonkneen · 2026-10-22
- Testing decision models like Jev and Drex Max for research triage: Drex Max heads to production — omarsar0 · 2026-10-22
- LlamaIndex releases OCRia-1, a 4B document-parsing VLM claiming SOTA on ParseBench at 87.4 — llama_index · 2026-10-22
- After MoE and MTP, local dense models haven't seen architectural speedups — Express_Quail_1493 · 2026-10-22