IEEE

MEDFIT-LLM: Medical Enhancements through Domain-Focused Fine Tuning of Small Language Models

Abstract: This research explores the efficacy of fine-tuning small Large Language Models (LLMs) for AI-based healthcare chatbots. We present a novel approach to dataset creation using synthetic data ...
IEEE

KnowSTU: Diagnosing Students’ Problem Behaviors Using Fine-Tuned LLM and RAG

Abstract: Students’ problem behaviors, which deviate from established school norms, can undermine both their well-being and academic achievement. Effectively addressing such behaviors often requires ...

Xiaomi's HarnessX rewrites its own AI scaffolding mid-task — and smaller models gain the most

Xiaomi's HarnessX autonomously rewrites AI agent harnesses mid-execution, delivering +14.5% avg performance gains — and +44% ...
GitHub

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning

To fully reproduce our experiments, please refer to ReproduceExps.md. To download our training data and reproduce the plots in the paper, please refer to ...
GitHub

ecu-tuning

Comprehensive database of components found in Honda OBD0 and OBD1 ECUs, with searchable web interface at ecucomponents.hondabase.com. Includes technical specs, compatibility info, and usage notes for ...
Mercury News

Gov. Gavin Newsom fined $31,500 by state watchdog for late reporting of $5.5 million in behested payments tied to LA wildfires

Gov. Gavin Newsom has agreed to pay a $31,500 fine after California’s political watchdog agency found he’d missed deadlines to report more than $5.5 million in donations made by major corporations at ...