arXiv:2510.19056v1 Announce Type: new Abstract: Federated Learning (FL) enables decentralized model training across multiple clients without exposing local data, but its distributed feature makes it vulnerable to backdoor attacks. Despite early FL backdoor attacks modifying entire models, recent studies have…
arXiv:2507.16814v2 Announce Type: replace Abstract: Enhancing large vision-language models (LVLMs) with visual slow-thinking reasoning is crucial for solving complex multimodal tasks. However, since LVLMs are mainly trained with vision-language alignment, it is difficult to adopt on-policy reinforcement learning (RL) to…
arXiv:2510.19093v1 Announce Type: new Abstract: Transferring the optimal learning rate from small to large neural networks can enable efficient training at scales where hyperparameter tuning is otherwise prohibitively expensive. To this end, the Maximal Update Parameterization (muP) proposes a learning…
arXiv:2510.13656v2 Announce Type: replace Abstract: Class imbalance, where certain classes have insufficient data, poses a critical challenge for robust classification, often biasing models toward majority classes. Distribution calibration offers a promising avenue to address this by estimating more accurate class…
arXiv:2510.19099v1 Announce Type: new Abstract: Curriculum learning (CL) – ordering training data from easy to hard – has become a popular strategy for improving reasoning in large language models (LLMs). Yet prior work employs disparate difficulty metrics and training setups,…
arXiv:2411.13022v3 Announce Type: replace-cross Abstract: Physics-driven deep learning (PD-DL) approaches have become popular for improved reconstruction of fast magnetic resonance imaging (MRI) scans. Though PD-DL offers higher acceleration rates than existing clinical fast MRI techniques, their use has been limited…
arXiv:2510.19105v1 Announce Type: new Abstract: Kolmogorov-Arnold Networks (KANs) replace scalar weights with per-edge vectors of basis coefficients, thereby boosting expressivity and accuracy but at the same time resulting in a multiplicative increase in parameters and memory. We propose MetaCluster, a…
arXiv:2506.05735v4 Announce Type: replace-cross Abstract: Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of isolated facts, often overlooking latent inferential dependencies and the non-deterministic nature of…
arXiv:2510.19119v1 Announce Type: new Abstract: In networked environments, users frequently share recommendations about content, products, services, and courses of action with others. The extent to which such recommendations are successful and adopted is highly contextual, dependent on the characteristics of…
arXiv:2509.23426v2 Announce Type: replace-cross Abstract: AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because they are bespoke, tied to rigid workflows, and lack shared environments that unify tools, data,…
