About
Research & Development
RoGBot: A New Era in Bot Detection Without Social Network Links
TLDR: RoGBot is a novel bot detection framework that overcomes the limitation of relying on follower-following data. It combines semantic features from tweets (using...
Research & Development
ELBO-KTO: Aligning Diffusion Language Models with Unpaired Human Feedback
TLDR: A new research paper introduces ELBO-KTO, a novel framework for aligning Diffusion Language Models (dLLMs) with human preferences using unpaired feedback. Unlike traditional...
Research & Development
Sparsity and Specialization: Making Sense of Mixture of Experts Models
TLDR: Mixture of Experts (MoE) models, crucial for large language models, are often poorly understood mechanistically. This research introduces "network sparsity" as a key...
Research & Development
Disentangling Biases in AI Reward Models for More Reliable Language Models
TLDR: A new research paper introduces CARD (Causal Reward Disentanglement), a framework to mitigate biases in large language model (LLM) reward models. Instead of...
Research & Development
OraPlan–SQL: Advancing Natural Language to SQL Conversion with Intelligent Planning
TLDR: OraPlan–SQL is a leading framework for converting complex, bilingual natural language queries into SQL. It uses a two-agent system (Planner and SQL agent)...
Research & Development
New Framework Enhances Wildfire Prediction with Social Media and Satellite Data
TLDR: A new Multimodal Fire Spread Prediction Framework (MFiSP) integrates social media data and remote sensing observations to significantly improve wildfire forecasting accuracy. By...