arXiv:2512.18246v1 Announce Type: new Abstract: Behavioral cloning is a widely adopted approach for offline policy learning from expert demonstrations. However, the large scale of offline behavioral datasets often results in computationally intensive training when used in downstream tasks. In this…
arXiv:2511.23083v5 Announce Type: replace Abstract: High-capacity kernel Hopfield networks exhibit a textit{Ridge of Optimization} characterized by extreme stability. While previously linked to textit{Spectral Concentration}, its origin remains elusive. Here, we analyze the network dynamics on a statistical manifold, revealing that…
arXiv:2512.18248v1 Announce Type: new Abstract: The low-rank adaptation (LoRA) algorithm for fine-tuning large models has grown popular in recent years due to its remarkable performance and low computational requirements. LoRA trains two “adapter” matrices that form a low-rank representation of…
arXiv:2512.16963v2 Announce Type: replace Abstract: Current Large Language Models (LLMs) face three major challenges: context length limitations, high inference costs, and catastrophic forgetting during continual learning. While Mixture-of-Experts (MoE) architectures mitigate some of these conflicts, their routing mechanisms typically rely…
arXiv:2512.18266v1 Announce Type: new Abstract: With the rapid advancements in big data technologies, the Databricks platform has become a cornerstone for enterprises and research institutions, offering high computational efficiency and a robust ecosystem. However, managing the escalating operational costs associated…
arXiv:2410.16750v3 Announce Type: replace-cross Abstract: Variational Autoencoders (VAE) are popular generative models used to sample from complex data distributions. Despite their empirical success in various machine learning tasks, significant gaps remain in understanding their theoretical properties, particularly regarding convergence guarantees.…
arXiv:2512.18275v1 Announce Type: new Abstract: Federated Learning (FL) methods are often designed for specific client participation patterns, limiting their applicability in practical deployments. We introduce the FedSUM family of algorithms, which supports arbitrary client participation without additional assumptions on data…
arXiv:2506.16289v2 Announce Type: replace-cross Abstract: This paper explores the relationship between the condition number of a neural network’s weight tensor and the extent of information encoded by the associated processing unit, viewed through the lens of information theory. It argues…
arXiv:2512.18295v1 Announce Type: new Abstract: Continual graph learning (CGL) aims to enable graph neural networks to incrementally learn from a stream of graph structured data without forgetting previously acquired knowledge. Existing methods particularly those based on experience replay typically store…
arXiv:2510.17638v2 Announce Type: replace-cross Abstract: Forecasting is not only a fundamental intellectual pursuit but also is of significant importance to societal systems such as finance and economics. With the rapid advances of large language models (LLMs) trained on Internet-scale data,…
