About
Research & Development
Boosting Financial AI Accuracy with Multi-Perspective Retrieval and Intelligent Agents
TLDR: This research introduces a novel framework for financial question-answering that combines Agentic AI with Multi-HyDE, a system generating multiple, distinct queries for enhanced...
Research & Development
Evaluating Legal Summaries Through Diverse User Lenses: Introducing PersonaMatrix
TLDR: PersonaMatrix is a new evaluation framework for legal summarization that assesses summary quality from the perspective of different user types (personas) like litigators,...
Research & Development
Enhancing Robotic Action Recognition with Knowledge-Infused AI
TLDR: KRAST is a new method that improves robotic action recognition from videos by using vision-language models (VLMs) augmented with structured textual knowledge. It...
Research & Development
Unmasking the Vulnerability: How One Agent Can Sway Multi-Agent AI Decisions
TLDR: A new research paper introduces M-Spoiler, a framework demonstrating how an attacker with knowledge of only one agent in a multi-agent Large Language...
Research & Development
Advancing Autonomous Driving Perception with Query-based Splatting
TLDR: SQS is a new pre-training method for Sparse Perception Models (SPMs) in autonomous driving. It uses query-based 3D Gaussian splatting to learn fine-grained...
Research & Development
Next-Gen Cybersecurity: An Intelligent Honeypot for LDAP Using Large Language Models
TLDR: This research paper introduces an intelligent honeypot that leverages Large Language Models (LLMs) to simulate an LDAP server. The system is designed to...