3 papers
cs.LG2026
Topological Simplification in Predictive Coding Networks
Adam Shaw, Jiayu Li, Michael Sperling +2
We study the topology of learned representations in predictive coding networks (PCNs), a neuro-inspired bidirectional architecture, using a quantitative layer-wise persistent homol…
cs.LG2026
Hierarchical Synthetic Tabular Data Generation: A Hybrid Top-Down and Bottom-Up Framework
Junfeng Nie, Alvin Jin, Xiaohui Chen
Existing approaches for synthetic tabular data generation are based on either purely generative models or LLMs, both of which struggle with data heterogeneity, logical consistency,…
cs.LG2025
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…