模型与评测

Watts If? A Benchmark for Counterfactual Reasoning About the AI Data Center Buildout

arXiv:2610.21397v1 Announce Type: new Abstract: An AI data center is committed years before it draws a watt: a few discrete choices (grid or on-site gas, evaporative or dry cooling, which county to file in) fix its capital, water draw, and carbon path, and LLMs are now asked to h

Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs

arXiv:2610.21380v1 Announce Type: new Abstract: Reinforcement learning has brought strong gains to language model reasoning, but its improvements on visual tasks remain less consistent. One difficulty is that visual task failures can arise from different sources: the same benchma

When Is Muon Optimal? Radial Fragility and Minimax Geometry

arXiv:2610.21549v1 Announce Type: cross Abstract: Muon replaces a matrix gradient by an approximate polar factor and has shown strong empirical performance in neural-network training. The Isotropic Curvature Model (ICM) provides a curvature-based explanation for this update by as

Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline

Welcome Beam: a 501B open model you can own, customize, and scale