arXiv:2502.05684v3 Announce Type: replace Abstract: How can we effectively remove or ”unlearn” undesirable information, such as specific features or the influence of individual data points, from a learning outcome while minimizing utility loss and ensuring rigorous guarantees? We introduce a…
arXiv:2512.02303v1 Announce Type: new Abstract: While data augmentation is widely used to train symmetry-agnostic models, it remains unclear how quickly and effectively they learn to respect symmetries. We investigate this by deriving a principled measure of equivariance error that, for…
arXiv:2504.19602v3 Announce Type: replace Abstract: Federated Learning (FL) enables collaborative model training across decentralized clients, enhancing privacy by keeping data local. Yet conventional FL, relying on frequent parameter-sharing, suffers from high communication overhead and limited model heterogeneity. Distillation-based FL approaches…
arXiv:2512.02323v1 Announce Type: new Abstract: Boltzmann machines (BMs) are powerful energy-based generative models, but their heavy training cost has largely confined practical use to Restricted BMs (RBMs) trained with an efficient learning method called contrastive divergence. More accurate learning typically…
arXiv:2505.23337v3 Announce Type: replace Abstract: Industry-grade ML models are carefully designed to meet rapidly evolving serving constraints, which requires significant resources for model development. In this paper, we propose MatTA, a framework for training multiple accurate Student models using a…
arXiv:2512.02333v1 Announce Type: new Abstract: Retrieval-augmented models couple parametric predictors with non-parametric memories, but their use in streaming supervised learning with concept drift is not well understood. We study online classification in non-stationary environments and propose Retrieval-Augmented Memory for Online…
arXiv:2508.07114v2 Announce Type: replace Abstract: In this work, we introduce a new information-theoretic perspective on Multiple Instance Learning (MIL) for parameter estimation with i.i.d. data, and show that MIL can outperform single-instance learners in low-signal regimes. Prior work [Nachman and…
Preliminary studies find derivatives of the compound, known as verticillin A, can kill some types of glioma cells.
arXiv:2504.04634v3 Announce Type: replace-cross Abstract: Recent advances in dance generation have enabled the automatic synthesis of 3D dance motions. However, existing methods still face significant challenges in simultaneously achieving high realism, precise dance-music synchronization, diverse motion expression, and physical plausibility.…
arXiv:2511.17467v2 Announce Type: replace Abstract: We propose a novel framework for persona-based language model system, motivated by the need for personalized AI agents that adapt to individual user preferences. In our approach, the agent embodies the user’s “persona” (e.g. user…
