OpenSIR: Open-Ended Self-Improving Reasoner
Paper
•
2511.00602
•
Published
•
20
We do research in all core areas of natural language processing, including morphology, parsing, semantics, discourse, language generation, and machine translation. EdinburghNLP also has a strong track record of work at the interface of NLP with other areas, including speech technology, machine learning, computer vision, cognitive modeling, social media, information retrieval, robotics, bioinformatics, and educational technology.
OpenSIR: Open-Ended Self-Improving Reasoner
Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them