About
Research & Development
Unlocking Optimal Designs for Next-Gen Wireless Surfaces with AI
TLDR: This research introduces a Learning-based Two-Tier Architecture Discovery Framework (LTTADF) to design optimal Beyond-Diagonal Reconfigurable Intelligent Surfaces (BD-RIS) under real-world non-idealities like mutual...
Research & Development
Peer Review for Large Language Models: A Game Theory Approach
TLDR: This research introduces a game-theoretic framework for evaluating large language models (LLMs) through 'automatic mutual evaluation.' LLMs assess each other's outputs, and these...
Research & Development
NDM Framework: Enhancing Safety in Text-to-Image AI by Detecting Hidden Harmful Intent
TLDR: NDM (Noise-driven Detection and Mitigation) is a new framework designed to prevent text-to-image AI models from generating inappropriate content, especially from subtle or...
Research & Development
Hybrid Optimization Solver Delivers Unprecedented Speed and Trust for Power Grids
TLDR: A new hybrid optimization solver combines fast machine learning proxies with reliable classical solvers for large-scale economic dispatch problems in power grids. It...
Research & Development
Rubric-Guided AI Training for Better Medical Dialogue Systems
TLDR: ORBIT is a novel training framework that uses dynamically generated rubrics to incrementally train Large Language Models (LLMs) for complex, open-ended tasks, particularly...
Research & Development
Unlocking Individual Thought: A New Benchmark for Language Models
TLDR: HugAgent is a new benchmark designed to evaluate how well large language models (LLMs) can simulate individual human reasoning, rather than just population...