About
Research & Development
Enhancing Large Language Model Safety and Efficiency Through Intelligent Data Curation
TLDR: Pharmacist is a novel data curation solution that improves the safety and efficiency of Large Language Models (LLMs) against harmful fine-tuning. It achieves...
Research & Development
Enhancing Fire and Smoke Detection in Compact AI Models with Uncertainty and Visual Cues
TLDR: A new post-detection framework significantly improves fire and smoke detection in compact AI models like YOLOv5n and YOLOv8n. It refines detection confidence by...
Research & Development
SaFiRe: A Human-Inspired Approach to Understanding Complex Image Descriptions for Segmentation
TLDR: SaFiRe is a novel framework for Referring Image Segmentation (RIS) that addresses the limitations of current models in handling ambiguous language. Inspired by...
Research & Development
TyFlow: Guiding Language Models to Master Type Correctness in Code Generation
TLDR: TyFlow is a novel system that enables large language models (LLMs) to generate type-correct code by internalizing type reasoning. It achieves this through...
Research & Development
Robots Gain Adaptive Skills Through Uncertainty-Driven Foresight
TLDR: The UF-RNN is a novel AI model that enables robots to adapt to uncertain environments by actively simulating multiple future scenarios and selecting...
Research & Development
Audit-of-Understanding: A New Framework for Reliable Mathematical Reasoning in Language Models
TLDR: The Audit-of-Understanding (AoU) framework addresses reasoning-induced hallucinations in large language models (LLMs) by constraining inference to validated premises. It involves three phases: decomposing...