LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models Paper • 2609.32264 • Published 8 days ago • 44
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Paper • 2609.29845 • Published 10 days ago • 101
RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM Paper • 2607.11683 • Published Jul 13 • 150
Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models Paper • 2606.19297 • Published Jun 17 • 78
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering Paper • 2606.00683 • Published May 30 • 102
RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation Paper • 2605.04523 • Published May 6 • 47
Pisets: A Robust Speech Recognition System for Lectures and Interviews Paper • 2601.18415 • Published Jan 26 • 38