About
Research & Development
ToolACE-MT: Crafting Smarter AI Agent Conversations with Non-Autoregressive Generation
TLDR: ToolACE-MT is a novel non-autoregressive framework for generating high-quality, multi-turn, tool-using dialogues to train Large Language Model (LLM) agents. It addresses the inefficiencies...
Research & Development
LinguaSafe: Advancing Multilingual Safety Evaluation for Large Language Models
TLDR: LinguaSafe is a new, comprehensive benchmark designed to evaluate the safety of large language models (LLMs) across 12 diverse languages, including under-represented ones...
Research & Development
FedUNet: Enabling Diverse AI Models to Learn Together Efficiently
TLDR: FedUNet is a new federated learning framework that allows different AI models to train collaboratively without sharing all their data or requiring identical...
Research & Development
A New Approach to Identifying Data Outliers Using Randomized PCA Forests
TLDR: Researchers have developed a new unsupervised method for detecting outliers in data, called Randomized PCA Forest. This technique uses a collection of decision...
Research & Development
Bridging the Divide: A New Framework for Aligning AI and Human Evaluations
TLDR: Bridge is a new statistical framework that helps align Large Language Model (LLM) evaluations with human judgments. It models LLM deviations from human...
Applications & Use Cases
Unlocking Developer Engagement: Why Traditional Marketing Falls Short in a Tech-Driven World
TLDR: The realm of developer marketing is experiencing rapid expansion, yet many organizations are struggling to devise and implement effective strategies. Developers, who are...