Dimension-free deterministic equivalents and scaling laws for random feature regressionby Leonardo Defilippis, Bruno Loureiro, Theodor…
The Impact of Geometric Complexity on Neural Collapse in Transfer Learningby Michael Munn, Benoit Dherin,…
Information-theoretic Generalization Analysis for Expected Calibration Errorby Futoshi Futami, Masahiro FujisawaFirst submitted to arxiv on:…
Learning Beyond Pattern Matching? Assaying Mathematical Understanding in LLMsby Siyuan Guo, Aniket Didolkar, Nan Rosemary…
Learning to Discretize Denoising Diffusion ODEsby Vinh Tong, Trung-Dung Hoang, Anji Liu, Guy Van den…
Revisiting Counterfactual Regression through the Lens of Gromov-Wasserstein Information Bottleneckby Hao Yang, Zexu Sun, Hongteng…
ChatGPT Code Detection: Techniques for Uncovering the Source of Codeby Marc Oedingen, Raphael C. Engelhardt,…
Mosaic Memory: Fuzzy Duplication in Copyright Traps for Large Language Modelsby Igor Shilov, Matthieu Meeus,…
On the Convexity and Reliability of the Bethe Free Energy Approximationby Harald Leisenberger, Christian Knoll,…
Polyp Segmentation Generalisability of Pretrained Backbonesby Edward Sanderson, Bogdan J. MatuszewskiFirst submitted to arxiv on:…