arXiv:2602.18628v1 Announce Type: new Abstract: Large language models store all learned knowledge in a single, fixed weight vector. Teaching a model new capabilities requires modifying those same weights, inevitably degrading previously acquired knowledge. This fundamental limitation, known as catastrophic forgetting,…
arXiv:2504.02996v2 Announce Type: replace Abstract: Methods addressing Learning with Noisy Labels (LNL) and multi-source Domain Generalization (DG) use training techniques to improve downstream task performance in the presence of label noise or domain shifts, respectively. Prior work often explores these…
arXiv:2602.18637v1 Announce Type: new Abstract: $textit{Objective.}$ Accurate neural decoding of locomotion holds promise for advancing rehabilitation, prosthetic control, and understanding neural correlates of action. Recent studies have demonstrated decoding of locomotion kinematics across species on motorized treadmills. However, efforts to…
arXiv:2506.00486v4 Announce Type: replace Abstract: Despite rapid progress in large language models (LLMs), the statistical structure of their weights, activations, and gradients-and its implications for initialization, training dynamics, and efficiency-remains largely unexplored. We empirically show that these quantities in LLMs…
arXiv:2602.18639v1 Announce Type: new Abstract: World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recent latent predictive architectures (JEPAs), including the DINO world model (DINO-WM), display a…
arXiv:2509.03738v3 Announce Type: replace Abstract: We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate directly in infinite-dimensional function spaces. We generalize the linear representation hypothesis to a functional representation hypothesis, enabling concept learning beyond…
arXiv:2602.18645v1 Announce Type: new Abstract: Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full series or appear in a few short intervals, so the model…
arXiv:2510.01650v2 Announce Type: replace Abstract: Neural network pruning is a promising technique to mitigate the excessive computational and memory requirements of large language models (LLMs). Despite its promise, however, progress in this area has diminished, as conventional methods are seemingly…
arXiv:2602.18647v1 Announce Type: new Abstract: Training diffusion models typically relies on manually tuned noise schedules, which can waste computation on weakly informative noise regions and limit transfer across datasets, resolutions, and representations. We revisit noise schedule allocation through an information-theoretic…
arXiv:2511.04934v2 Announce Type: replace Abstract: Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing private, toxic, illegal, or copyrighted content. Despite rapid progress, in this work we show…
