NuExtract3
PulseAugur coverage of NuExtract3 — every cluster mentioning NuExtract3 across labs, papers, and developer communities, ranked by signal.
- 2026-08-24 research_milestone NuExtract3 model achieved improved precision after fine-tuning with LoRA on a pilot corpus. source
- 2026-05-25 product_launch Numind released the NuExtract3 model for document understanding.
- 2026-05-22 product_launch Numind released the open-weight 4B visual language model NuExtract3. source
- 2026-05-22 product_launch Numind released NuExtract3, a 4B open-weight visual language model for document extraction. source
- 2026-04-29 product_launch numind has released the NuExtract3 model for document understanding. source
1 day(s) with sentiment data
-
NuExtract3 model sees precision boost after LoRA fine-tuning
Researchers have fine-tuned the NuExtract3 model using LoRA on a pilot corpus of 624 training and 44 evaluation books. This process significantly boosted the model's precision from 0.61 to 0.76, while recall remained st…
-
Datalab's Lift 9B model leads in schema-first PDF extraction
Datalab's Lift is a new 9-billion parameter vision-language model designed for schema-first document extraction. Unlike traditional methods that first parse documents into intermediate formats before extracting fields, …
-
Local AI Tools Improve: llama.cpp Fix, NuExtract3 VLM, Qwen3.6 Speed
This week's AI news includes a critical fix for checkpoint creation in the llama.cpp server, enhancing its reliability for long-running agentic tasks. Additionally, NuExtract3 has been released as an open-weight 4B Visi…
-
Numind releases NuExtract3, a 4B open-weight VLM for document extraction
Numind has released NuExtract3, an open-weight 4B visual language model designed for extracting information from complex documents. Built on Qwen3.5-4B and licensed under Apache-2.0, this model can convert document imag…
-
Numind releases NuExtract3 for document understanding
Numind has released NuExtract3, a 4-billion parameter vision-language model designed for document understanding. This model excels at structured information extraction and converting images to Markdown, making it useful…