About
Research & Development
Conditional-t3VAE: A New Approach for Fair Image Generation in Imbalanced Datasets
TLDR: Conditional-t3VAE (C-t3VAE) is a novel generative model that addresses class imbalance in datasets by ensuring equitable latent space allocation for all classes. Unlike...
Research & Development
Securing and Safeguarding AI-Driven Robots: A Unified Framework for Reliable Operation
TLDR: This paper introduces a unified framework to enhance the reliability of robotic systems integrated with Large Language Models (LLMs). It addresses both security...
Research & Development
Crafting Unique Narratives: A New Decoding Strategy for LLMs
TLDR: A new decoding strategy called Avoidance Decoding helps Large Language Models generate more diverse and less repetitive multi-branch stories. It works by penalizing...
Research & Development
New Benchmark Challenges AI’s Understanding of Space
TLDR: The RocketScience benchmark, a new open-source dataset of real-world contrastive image-text pairs, reveals significant limitations in how Vision-Language Models (VLMs) understand spatial relationships...
Research & Development
Unlocking Deeper Insights: A New Approach to Forecasting Multivariate Time Series
TLDR: ST-Hyper is a novel deep learning model for multivariate time series forecasting that addresses the limitation of existing methods by modeling high-order dependencies...
Research & Development
Balancing the News: A Neuro-Symbolic Approach to Diverse Recommendations
TLDR: This research paper proposes a new approach to diversify news recommendations by considering multiple aspects (like topic and framing) across different recommendation modes...