Archives AI News

LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning

arXiv:2507.20999v3 Announce Type: replace Abstract: Large-scale generative models like DeepSeek-R1 and OpenAI-O1 benefit substantially from chain-of-thought (CoT) reasoning, yet pushing their performance typically requires vast data, large model sizes, and full-parameter fine-tuning. While parameter-efficient fine-tuning (PEFT) helps reduce cost, most…

Minimax optimal transfer learning for high-dimensional additive regression

arXiv:2509.06308v2 Announce Type: replace-cross Abstract: This paper studies high-dimensional additive regression under the transfer learning framework, where one observes samples from a target population together with auxiliary samples from different but potentially related regression models. We first introduce a target-only…