About
Research & Development
Decoding AI’s Medical Decisions: A New Dataset and LLM-Guided Explanations for Clinical Coding
TLDR: This research evaluates how well AI models explain their medical coding decisions, focusing on "faithfulness" (how accurately explanations reflect model reasoning) and "plausibility"...
Research & Development
Unpacking AI Sycophancy: A Bayesian Perspective on LLM Rationality
TLDR: This research introduces a Bayesian framework to quantify sycophancy in large language models (LLMs) as deviations from rational behavior. Unlike previous methods that...
Research & Development
PowerChain: AI System Automates Complex Grid Analysis for Utilities
TLDR: PowerChain is a novel agentic AI system designed to automate complex distribution grid analysis. It uses large language models (LLMs) to dynamically generate...
Research & Development
MaRVL-QA: Uncovering the Limits of AI in Visual Mathematical Reasoning
TLDR: MaRVL-QA is a new benchmark that evaluates Multimodal Large Language Models (MLLMs) on deep mathematical and spatial reasoning directly from images, using semantically...
Research & Development
Brain-Inspired AI Agents Gain Human-Like Spatial Intelligence for Navigation and Manipulation
TLDR: BSC-Nav is a new brain-inspired framework that equips embodied AI agents with structured spatial memory, mimicking how biological brains process space through landmarks,...
Research & Development
AI Model VIPER-R1 Learns to Interpret Visual Cues for Physics Equation Discovery
TLDR: VIPER-R1 is a new multimodal AI framework that mimics a physicist's approach to discovering physical laws. It integrates visual data (like motion plots)...