Open-weight & owned stack · Training tuning

Structure-Aware Fine-Tuning Improves AMR-to-Text Generation

Sep 11, 2026

SAFT introduced graph-sensitive positional encodings for fine-tuning pretrained language models on AMR-to-text generation.

Read the original at lacuna.tiptreesystems.comOpens the publisher's site in a new tab

More in Open-weight & owned stack

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