3 papers
cs.CL2026
Doc-to-LoRA: Learning to Instantly Internalize Contexts
Rujikorn Charakorn, Edoardo Cetin, Shinnosuke Uesaka +1
Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of…
cs.CL2025
ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
Robert Tjarko Lange, Yuki Imajuku, Edoardo Cetin
We introduce ShinkaEvolve: a new open-source framework leveraging large language models (LLMs) to advance scientific discovery with state-of-the-art performance and unprecedented e…
cs.LG2025
Text-to-LoRA: Instant Transformer Adaption
Rujikorn Charakorn, Edoardo Cetin, Yujin Tang +1
While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation o…