PolyAI Releases Dialog-RSN-1: An Audio-Native Dialog Model That Fuses Turn-Taking, Speech Recognition, Function Calling, And Response
juillet 31, 2026admin NUAI,Committee,Actualités,Uncategorized(0)PolyAI has introduced Dialog-RSN-1, a dialog model that perceives the caller’s audio directly instead of...
Political Leaning and Politicalness Classification of Texts
juillet 21, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2507.13913v1 Announce Type: new Abstract: This paper addresses the challenge of automatically classifying text according...
Pokee AI Releases Pokee-Isaac 28B: A 10M-Token Context Agentic Model Built to Run Inside the Customer Boundary
août 8, 2026admin NUAI,Committee,Actualités,Uncategorized(0)Long-horizon agents accumulate context faster than they resolve tasks. Every tool output, observation, and intermediate...
PoE-World + Planner Outperforms Reinforcement Learning RL Baselines in Montezuma’s Revenge with Minimal Demonstration Data
juin 21, 2025admin NUAI,Committee,Actualités,Uncategorized(0)The Importance of Symbolic Reasoning in World Modeling Understanding how the world works is key...
PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving
juillet 11, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2507.07495v1 Announce Type: new Abstract: Recently, decomposing complex problems into simple subtasks–a crucial part of...
Pie day links
avril 17, 2026admin NUAI,Committee,Actualités,Uncategorized(0)Pie Day at the Massachusetts Institute of Tasteology...
PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problems
novembre 6, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2508.00079v2 Announce Type: replace Abstract: The discipline of physics stands as a cornerstone of human...
Physical Intelligence Team Unveils MEM for Robots: A Multi-Scale Memory System Giving Gemma 3-4B VLAs 15-Minute Context for Complex Tasks
mars 4, 2026admin NUAI,Committee,Actualités,Uncategorized(0)Current end-to-end robotic policies, specifically Vision-Language-Action (VLA) models, typically operate on a single observation or...
Phonetic accommodation and inhibition in a dynamic neural field model
mai 12, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2502.01210v2 Announce Type: replace Abstract: Short-term phonetic accommodation is a fundamental driver behind accent change...
