arXiv:2502.05709v3 Announce Type: replace-cross Abstract: Time series prediction underpins a broad range of downstream tasks across many scientific domains. Recent advances and increasing adoption of black-box machine learning models for time series prediction highlight the critical need for uncertainty quantification. While conformal prediction has gained attention as a reliable uncertainty quantification method, conformal prediction for time series faces two key challenges: (1) textbf{leveraging correlations in observations and non-conformity scores to overcome the exchangeability assumption}, and (2) textbf{constructing prediction […]

Ver mais

Recently, Transformer-based architectures have advanced meteorological prediction. However, this position-centric tokenizer conflicts with the core principle of meteorological systems, where the weather phenomena undoubtedly involve synergistic interactions among multiple elements while positional information constitutes merely a component of the boundary conditions. This paper focuses primarily on the task of precipitation nowcasting and develops an efficient distribution-centric Meteorological Tokenization (MeTok) scheme, which spatially sequences to group similar meteorological features. Based on the rearrangement, realigned group learning enhances robustness across […]

Ver mais

NVIDIA founder and CEO Jensen Huang took the stage at the Fontainebleau Las Vegas to open CES 2026, declaring that AI is scaling into every domain and every device. “Computing has been fundamentally reshaped as a result of accelerated computing, as a result of artificial intelligence,” Huang said. “What that means is some $10 trillion or so of the last decade of computing is now being modernized to this new way of doing computing.” Huang unveiled Rubin, NVIDIA’s […]

Ver mais

arXiv:2604.14158v1 Announce Type: new Abstract: Current evaluations of long-term memory in LLMs are fundamentally static. By fixating on simple retrieval and short-context inference, they neglect the multifaceted nature of complex memory systems, such as dynamic state tracking and hierarchical reasoning in continuous interactions. To overcome these limitations, we propose MemGround, a rigorous long-term memory benchmark natively grounded in rich, gamified interactive scenarios. To systematically assess these capabilities, MemGround introduces a three-tier hierarchical framework that evaluates Surface State Memory, […]

Ver mais

The data was fine. For now. That was the problem. Sharing something from my own work that stuck with me. Hope it resonates. I was not looking for it. I was in the middle of a data programme. SQL scripts, Power BI dashboards, process maps, the usual. Head down in the analysis, trying to make sense of what the systems actually held versus what people thought they held. Those two things are often quite different and the gap […]

Ver mais

In this quiz, you’ll test your understanding of Python’s Counter: The Pythonic Way to Count Objects. By working through this quiz, you’ll revisit how to create Counter objects, update counts, find most common elements, and use counters as multisets with arithmetic operations. This quiz covers practical Counter tasks such as constructing counters from different data types, accessing counts, and working with multiset operations. If you want a deeper walkthrough, review the tutorial linked above. [ Improve Your Python […]

Ver mais

Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data. However, data heterogeneity across clients leads to client drift, which degrades the overall generalization performance of the model. This effect is further compounded by overemphasis on poorly performing clients. To address this problem, we propose FedVG, a novel gradient-based federated aggregation framework that leverages a global validation set to guide the optimization process. Such a global validation set can be established using readily […]

Ver mais