About
Research & Development
Advancing AI Safety: A Scalable Approach to Probabilistic Robustness for Semantic Segmentation
TLDR: Researchers from Vanderbilt University have developed a new probabilistic verification framework to assess the robustness of Semantic Segmentation Networks (SSNs) against adversarial attacks....
Research & Development
Enhancing Video Question Answering with Structured Scene Graphs
TLDR: A new framework, SG-VLM, improves video question answering by integrating symbolic scene graphs into existing Vision Language Models (VLMs). It generates, selects, and...
Research & Development
Simulating Human Perspective Taking in AI: A Developmental Approach
TLDR: A research paper introduces an extension to the PerspAct system, integrating Large Language Models (LLMs) with Selman's theory of developmental perspective taking. The...
Research & Development
Simulating Intelligent Attacks to Strengthen Robot Patrol Security
TLDR: This research introduces a Time-Constrained Machine Learning (TCML) adversary model designed to test the vulnerabilities of multi-robot patrol systems. This AI-based attacker learns...
Research & Development
Unlocking Generalizable Expert Behavior: A New Approach to Inverse Reinforcement Learning
TLDR: This research paper addresses the challenge of generalizing expert behavior using Inverse Reinforcement Learning (IRL), where multiple reward functions can explain the same...
Research & Development
AI’s Role in Mental Health: High Ratings, Human Preference
TLDR: A study comparing LLM-generated mental health responses with human therapist responses found that LLMs (ChatGPT, Gemini, Llama) produced longer, more readable, and positively...