NeurIPS Review Controversies and the Edge of Native Numerical PFNs

Discussions highlight flawed NeurIPS reviews demanding un-falsifiable claims within budget, while expert Gael Varoquaux notes that natively numerical PFNs outperform post-trained LLMs on large tabular data.

2026-07-26 ~ 2026-07-26 · 2 related posts

• NeurIPS reviewers are asking claims that are impossible to disprove on budget — roydanroy · 2026-07-26
• PFNs use native numeric architectures, while post-trained LLMs lag on larger tables — GaelVaroquaux · 2026-07-26