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
arXiv:2505. 16077v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features.
By Soham Gadgil, Chris Lin, Su-In Lee
arXiv:2607. 09371v1 Announce Type: cross Abstract: Flexible machine-learning methods can be sensitive to hidden confounding: they may learn associations induced by unobserved confounders rather than stable signals.
By Andrea Nava, Peter B\"uhlmann, Fabio Sigrist
arXiv:2606. 28460v1 Announce Type: cross Abstract: Data-driven modeling in real-world regression tasks often suffers from limited training samples, high collection costs, and noisy observations.
By Hossein Mohebbi, Oliver Schulte, Ke Li, Pascal Poupart
arXiv:2609.24126v1 Announce Type: cross
Abstract: Black-box machine learning models increasingly deliver strong predictions, but extracting useful information from them, such as a set of important fe...
By Xuhui Liu, Lili Zheng
arXiv:2608. 03111v1 Announce Type: new Abstract: Double descent is commonly studied by scaling an explicit capacity parameter, such as neural-network width.
By Ryuichi Kanoh
arXiv:2606. 18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model.
By Ningyuan Shi, Zhipeng Zhou, Hao Wang, Chunyan Miao, Peilin Zhao
arXiv:2606. 16050v1 Announce Type: cross Abstract: Robust deep learning under heavy-tailed and impulsive noise remains challenging because conventional losses such as mean squared error (MSE) exhibit unbounded sensitivity to outliers.
By Mainak Kundu, Ria Kanjilal, Ismail Uysal
SPARCL introduces a spectral partitioned analytic continual learning method that addresses forgetting in analytic class‑incremental learning. By decomposing the running autocorrelation into a high‑energy core and a residual complement, SPARCL freezes core components for old classes and updates only the residual block, ensuring closed‑form updates with an invariance guarantee. Experiments on CIFAR‑100, CUB‑200, ImageNet‑R, and ImageNet‑A with a frozen ViT‑B/16 protocol show that SPARCL narrows the performance gap between classical analytic learners and strong representation matchers while complementing sparse feature‑decorrelation approaches.
By James Hartley, Zeropy Surio, Daniel Whitmore, Hannah Clarke, Thomas Reed
arXiv:2608.30699v1 Announce Type: cross
Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to...
By Yue Cheng, Jiajun Zhang, Xiaohui Gao, Weiwei Xing, Zhanxing Zhu
The paper proposes a sensitivity‑aware residual‑stream pruning method for large language models that goes beyond minimizing activation reconstruction error. By using a second‑order approximation of output KL divergence, the authors derive a spectral upper bound that selects pruning subspaces based on both activation covariance and output sensitivity, enabling efficient eigendecomposition. Experiments on instruction‑tuned language models show that this approach consistently reduces calibration KL divergence, improves perplexity, and enhances downstream task performance across various compression levels.
By Chayne Thrash, Kevin Chen, Soheil Kolouri
arXiv:2607. 10391v1 Announce Type: cross Abstract: Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks.
By Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi, Ignacio Meza De la Jara, Sebastian Doerrich, Marco Lents, Christian Ledig