arXiv:2512.00229v1 Announce Type: new Abstract: Deep neural networks often struggle to recognize when an input lies outside their training experience, leading to unreliable and overconfident predictions. Building dependable machine learning systems therefore requires methods that can both estimate predictive textit{uncertainty}…
arXiv:2512.00239v1 Announce Type: new Abstract: The effectiveness of self-supervised learning (SSL) for physiological time series depends on the ability of a pretraining objective to preserve information about the underlying physiological state while filtering out unrelated noise. However, existing strategies are…
arXiv:2512.00196v1 Announce Type: new Abstract: Many tasks require mapping continuous input data (e.g. images) to discrete task outputs (e.g. class labels). Yet, how neural networks learn to perform such discrete computations on continuous data manifolds remains poorly understood. Here, we…
arXiv:2512.00207v1 Announce Type: new Abstract: The success of large language models (LLMs) can be attributed in part to their ability to efficiently store factual knowledge as key-value mappings within their MLP parameters. Recent work has proposed explicit weight constructions to…
arXiv:2512.00191v1 Announce Type: new Abstract: Interpreting seismic horizons is a critical task for characterizing subsurface structures in hydrocarbon exploration. Recent advances in deep learning, particularly U-Net-based architectures, have significantly improved automated horizon tracking. However, challenges remain in accurately segmenting complex…
arXiv:2512.00181v1 Announce Type: new Abstract: Tabular data drive most real-world machine learning applications, yet building general-purpose models for them remains difficult. Mixed numeric and categorical fields, weak feature structure, and limited labeled data make scaling and generalization challenging. To this…
arXiv:2512.00170v1 Announce Type: new Abstract: High-dimensional spaces have challenged Bayesian optimization (BO). Existing methods aim to overcome this so-called curse of dimensionality by carefully encoding structural assumptions, from locality to sparsity to smoothness, into the optimization procedure. Surprisingly, we demonstrate…
arXiv:2511.00739v2 Announce Type: replace-cross Abstract: Agentic AI frameworks add a decision-making orchestrator embedded with external tools, including web search, Python interpreter, contextual database, and others, on top of monolithic LLMs, turning them from passive text oracles into autonomous problem-solvers that…
arXiv:2512.00242v1 Announce Type: new Abstract: Sheaf Neural Networks equip graph structures with a cellular sheaf: a geometric structure which assigns local vector spaces (stalks) and a linear learnable restriction/transport maps to nodes and edges, yielding an edge-aware inductive bias that…
arXiv:2512.01188v1 Announce Type: cross Abstract: A robot’s instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly acting to gain the missing information. Today’s standard robot learning techniques struggle to produce…
