About
Research & Development
Unveiling Optimal Comparison Strategies: An Empirical Look at Decision Making
TLDR: This research paper presents an experimental validation of optimal patterns and sequences for pairwise comparisons, using a color selection task with 301 participants....
Research & Development
OmniMRI: A Unified AI Model for Comprehensive MRI Analysis
TLDR: OmniMRI is a new AI foundation model that unifies various Magnetic Resonance Imaging (MRI) tasks, from image reconstruction and segmentation to abnormality detection,...
Research & Development
Enhancing LLM Alignment: A Novel Method to Combat Over-Optimization
TLDR: Weights-Rotated Preference Optimization (RoPO) is a new algorithm designed to improve Large Language Model (LLM) alignment by addressing the 'reward hacking' problem in...
Research & Development
Unveiling Opponent Strategies: A New Algorithm for Consistent Learning in Imperfect-Information Games
TLDR: A new research paper introduces FMAP, an algorithm designed for consistent opponent modeling in imperfect-information games. It addresses the critical flaw of existing...
Research & Development
Automating Database Structure with AI: Introducing Miffie
TLDR: Miffie is a novel framework that automates database schema normalization using a dual-model self-refinement architecture powered by large language models (LLMs). It employs...
Research & Development
Dynamic Image Creation: Aligning Text-to-Image Models with Evolving User Tastes
TLDR: This research introduces a training-free framework for instant preference-aligned text-to-image (T2I) generation. It uses multimodal large language models (MLLMs) to understand user preferences...