A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models Paper • 2605.08504 • Published 6 days ago • 5
The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability Paper • 2604.17698 • Published 24 days ago • 4
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published Mar 17 • 311
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale Paper • 2603.25040 • Published Mar 26 • 132
The Geometric Alignment Tax: Tokenization vs. Continuous Geometry in Scientific Foundation Models Paper • 2604.04155 • Published Apr 5 • 12