2 papers
cs.LG2026
Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks
Guillaume Corlouer, Avi Semler, Alexander Strang +1
Deep linear networks (DLNs) are used as an analytically tractable model of the training dynamics of deep neural networks. While gradient descent in DLNs is known to exhibit saddle-…
cs.LG2026
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…