most citedHardness of Learning Neural Networks under the Manifold Hypothesis

2 citations · 2 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG2026

CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models

Jeffrey G. Wang, Jason Wang, Marvin Li +1

Membership inference attacks (MIAs) are a canonical way to assess a machine learning model's privacy properties. Although several attempts have been made to evaluate MIAs on langua…

cs.LG2026

ERRORQUAKE: Heavy-Tailed Error Severity Distributions in Open-Weight Large Language Models

Jason Z Wang

At matched accuracy, open-weight LLMs differ substantially in the shape of their error severity distribution -- a difference invisible to the scalar error rate. Hallucination bench…

cs.LG2026

The Evaluation Blind Spot: A Stereological Theory of Benchmark Coverage for Large Language Models

Jason Z Wang

We give a stereological theory of LLM benchmark coverage. For any suite with effective dimensionality d_eff, the visible Hausdorff distance between two convex capability profiles c…

cs.LG2026

The Verification Tax: Fundamental Limits of AI Auditing in the Rare-Error Regime

Jason Z Wang

The most cited calibration result in deep learning -- post-temperature-scaling ECE of 0.012 on CIFAR-100 (Guo et al., 2017) -- is below the statistical noise floor. We prove this i…

cs.LG2026

Yuan3.0 Ultra: A Trillion-Parameter Enterprise-Oriented MoE LLM

YuanLab. ai, :, Shawn Wu +25

We introduce Yuan3.0 Ultra, an open-source Mixture-of-Experts (MoE) large language model featuring 68.8B activated parameters and 1010B total parameters, specially designed to enha…

cs.LG20242 cited

Hardness of Learning Neural Networks under the Manifold Hypothesis

Bobak T. Kiani, Jason Wang, Melanie Weber

The manifold hypothesis presumes that high-dimensional data lies on or near a low-dimensional manifold. While the utility of encoding geometric structure has been demonstrated empi…