About
Research & Development
MCIF: A New Benchmark for Multilingual Multimodal AI Understanding
TLDR: MCIF (Multimodal Crosslingual Instruction Following) is a novel, human-annotated benchmark designed to evaluate multimodal large language models (MLLMs) in complex, real-world scenarios. Based...
Research & Development
Assessing LLM Therapists: A New Approach to Understanding Client Exploration
TLDR: A new framework called MIND VOYAGER is introduced to evaluate Large Language Model (LLM) therapists. Unlike previous methods that use overly compliant client...
Research & Development
Redefining Network Performance: A Survey on AI-Driven Multi-Dimensional Information Metrics
TLDR: A new survey introduces the "X of Information" continuum, a four-dimensional framework (temporal, quality/utility, reliability/robustness, network/communication) for evaluating information in next-generation networks. It...
Research & Development
Enhancing E-commerce Product Attribute Prediction with Compact AI Models and Unlabeled Data
TLDR: This research introduces a method to efficiently train small Vision Language Models (VLMs) for predicting product attributes in e-commerce. By using Parameter-Efficient Fine-Tuning...
Research & Development
Unveiling the Language of Salsa: A New Dataset for Embodied AI
TLDR: Researchers have introduced CoMPAS3D, the largest and most diverse motion capture dataset of improvised salsa dancing, featuring 3 hours of dances from 18...
Research & Development
KD-GAT: A Compact AI System for Detecting Cyberattacks in Car Networks
TLDR: KD-GAT is a new intrusion detection system for Controller Area Networks (CAN) in vehicles. It uses Graph Attention Networks (GATs) to analyze CAN...