About
Research & Development
Large Language Models Show Human-Like Logic Induction, Challenging Cognitive Theories
TLDR: A new study reveals that Large Language Models (LLMs) can learn and apply logical rules in a way that closely matches human behavior,...
Research & Development
Unlocking Dynamic Presentations: A New AI Approach for Slide Animation Comprehension
TLDR: This research introduces the first public dataset for slide animation modeling, consisting of 12,000 text-JSON-video triplets covering all PowerPoint effects. It also presents...
Research & Development
New Framework Uses Answer Set Programming to Identify Reasons for Logical Inconsistencies
TLDR: Researchers Mohimenul Kabir and Kuldeep S Meel introduce MUS-ASP, an Answer Set Programming (ASP)-based framework designed for the online enumeration and counting of...
Research & Development
J1-ENVS: A New Frontier for Legal AI Evaluation
TLDR: J1-ENVS is a novel interactive and dynamic legal environment designed to benchmark LLM-based legal agents across six real-world Chinese legal scenarios, categorized into...
Research & Development
HAWK: A New Framework for Seamless Multi-Agent AI Collaboration
TLDR: HAWK is a new hierarchical framework for multi-agent AI systems, addressing challenges in cross-platform interoperability, dynamic task scheduling, and efficient resource sharing. It...
Research & Development
MuSiC: Enhancing Recommendations for New Users with Multimodal Data and Local Insights
TLDR: MuSiC is a new cross-domain recommendation (CDR) model that addresses the cold-start problem by effectively using multimodal data (images, text) and 'side users'...