About
Research & Development
Exploring Autonomous LLM Agents: Beyond Fixed Tasks
TLDR: This research explores adapting pretrained LLM agents to operate in open-ended environments, where they generate their own tasks and interact persistently. While current...
Research & Development
Predicting Your Next Destination with Cognitive-Aware AI
TLDR: CoAST (Cognitive-Aligned Spatio-Temporal Large Language Models) is a new AI framework that enhances next Point-of-Interest (POI) prediction. It addresses the limitations of traditional...
Research & Development
Enhancing LLM Agent Reliability: A Fine-Grained Approach to Function Calling
TLDR: ToolPRM is a new framework that improves how large language models (LLMs) perform structured function calls. It uses a "process reward model" to...
Research & Development
RoboGPT-R1: A Two-Stage Approach for Advanced Robot Task Planning
TLDR: RoboGPT-R1 is a new two-stage training framework for robots to better understand and execute complex, multi-step instructions. It first uses supervised learning for...
Research & Development
LabOS: An AI Co-Scientist That Works Alongside Humans in the Lab
TLDR: LabOS is a pioneering AI co-scientist system that integrates advanced AI reasoning with physical laboratory experimentation through extended reality (XR) smart glasses. It...
Analytical Insights & Perspectives
Mexican CISOs Grapple with Escalating Cyber Threats and Generative AI Risks
TLDR: A recent Proofpoint study, 'Voice of the CISO 2025,' reveals that 80% of Chief Information Security Officers (CISOs) in Mexico anticipate a significant...