BLAST RADIUS

Open-weight & owned stack · Training tuning

Pretraining Filtering Builds Open-Weight Model Safeguards

Sep 12, 2026

An ICLR 2026 paper finds that filtering pretraining data can create tamper-resistant safeguards in open-weight language models.

Read the original at mlanthology.orgOpens the publisher's site in a new tab

More in Open-weight & owned stack

Z.ai publishes GLM-5.3 open weightsSep 8MiniMax H3 highlighted as open-weight multimodal modelSep 7InternLM releases 397B multimodal Intern-S2 modelSep 13DeepSeek Model Nearly Matches GPT-6 Astra DesignSep 10DeepSeek presents V4 FlashSep 8