CORE-STACK+ is a new meta‑learning framework for deep stacked generalization that tackles two key problems in heterogeneous vision ensembles: prediction‑space multicollinearity and calibration collapse. It introduces a four‑step preconditioning pipeline—kernelized redundancy filtering, a lightweight differentiable meta‑feature gate, a spectrum‑adaptive ridge penalty, and a Laplace‑approximate Bayesian blender—to jointly improve conditioning and calibration. Across six vision benchmarks, CORE‑STACK+ boosts accuracy, reduces model count and inference cost, and significantly lowers expected calibration error compared to existing methods.
By Noor Islam S. Mohammad
ExpTest is an autonomous learning‑rate controller that uses the training loss curve as an online signal to perform sequential statistical tests on theoretically motivated windows, detecting convergent behavior and triggering learning‑rate reductions. It combines a covariance‑based initial learning‑rate estimate, curvature‑motivated window sizing, and a two‑phase test‑driven decay, relying on the approximately exponential decay predicted under linearized network dynamics. Experiments on regression, classification, forecasting, and natural‑language tasks across various architectures show that ExpTest achieves competitive performance compared to hand‑tuned SGD baselines and recent learning‑rate‑free methods, without requiring manual initial learning‑rate selection or predefined scheduling.
By Zan Chaudhry, Naoko Mizuno
arXiv:2605. 18629v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features.
By Micha{\l} Brzozowski, Neo Christopher Chung
arXiv:2609.15643v1 Announce Type: new
Abstract: Flow-matching diffusion models have recently emerged as a strong paradigm for high-fidelity visual generation. However, their prohibitively high fine-t...
By Jiayang Gu, Zheng Fang, Lichaun Xiang, Fanghui Liu, Xu Cai, Hongkai Wen
arXiv:2606. 05139v1 Announce Type: new Abstract: The rapid advancement of high-throughput sequencing has led to large, high-dimensional omics datasets.
By Luca Thale-Bombien, Jan Ewald, Ralf K\"onig, Aaron Klein
arXiv:2606. 07954v1 Announce Type: cross Abstract: Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains.
By Prayas Agrawal, Prateek Chanda, Ishita Khatri, Ganesh Ramakrishnan, Bamdev Mishra, Pratik Jawanpuria