About
Research & Development
Decoding the Kitchen: How AI Combines Sight, Sound, and Motion to Understand Cooking
TLDR: This research presents a multi-modal AI system that interprets cooking activities from video by combining object segmentation, hand action recognition, audio transcription, and...
Research & Development
Beyond Prompt Crafting: Automating Rigorous Systematic Literature Reviews
TLDR: A new research paper introduces a declarative framework to make AI-assisted Systematic Literature Reviews (SLRs) reliable and reproducible. It addresses the 'prompt fragility'...
Research & Development
Traj-MLLM: Using Multimodal AI to Analyze Human Movement Data
TLDR: Traj-MLLM is a novel, training-free framework that applies Multimodal Large Language Models (MLLMs) to analyze human trajectory data. It addresses the limitations of...
Research & Development
Mapping Training Data to Enhance Generative AI Safety
TLDR: Generative Data Cartography (GenDataCarto) is a new data-centric framework that helps identify and mitigate memorization risks in generative AI models. It assigns each...
Research & Development
Building Trustworthy AI: A Framework for Private, Verifiable, and Auditable Systems
TLDR: Tobin South's doctoral thesis presents a comprehensive framework for creating secure, accountable, and privacy-preserving AI systems. It addresses critical challenges in AI development...
Research & Development
AEGIS: A New Automated Framework for Defending Against LLM Prompt Injection Attacks
TLDR: AEGIS is an automated co-evolutionary framework designed to defend Large Language Models (LLMs) against prompt injection attacks. It iteratively optimizes both attack and...