About
Research & Development
Unveiling CETVEL: A New Benchmark for Turkish Language Models
TLDR: CETVEL is a new, comprehensive benchmark for evaluating Turkish LLMs, featuring 23 diverse tasks across understanding and generation, with a strong focus on...
Research & Development
Addressing Age Bias in Medical AI: Introducing the PediatricsMQA Benchmark
TLDR: A new multi-modal benchmark, PediatricsMQA, has been developed to evaluate and improve the performance of large language models (LLMs) and vision-augmented LLMs (VLMs)...
Research & Development
SafeSpace: A Unified Platform for Online Safety and Emotional Health
TLDR: SafeSpace is a web application that integrates three key modules to enhance digital safety and emotional well-being: toxicity detection in chats and screenshots...
Research & Development
Boosting Prediction Accuracy: A New Method Using Pairwise Comparisons to Refine Regression Models
TLDR: RankRefine is a novel, model-agnostic method that improves the accuracy of existing regression predictions, especially in data-scarce situations. It works by combining a...
Research & Development
Advancing AI for Real-World Challenges: Zero-Shot Reinforcement Learning Under Practical Constraints
TLDR: This research explores how to make Zero-Shot Reinforcement Learning (ZSRL) practical for real-world problems by addressing three key constraints: low-quality data, partial observability,...
Research & Development
Boosting Language Model Math Abilities Through Data Analysis
TLDR: The FLAMES framework systematically analyzes and optimizes synthetic data generation for improving LLM math reasoning. It identifies that complexity-enhancing agents and broad data...