arXiv:2502.11682v2 Announce Type: replace Abstract: Strong Differential Privacy (DP) and Optimization guarantees are two desirable properties for a method in Federated Learning (FL). However, existing algorithms do not achieve both properties at once: they either have optimal DP guarantees but…
arXiv:2603.04458v1 Announce Type: new Abstract: Datasets composed of numerical and categorical attributes (also called mixed data hereinafter) are common in real clustering tasks. Differing from numerical attributes that indicate tendencies between two concepts (e.g., high and low temperature) with their…
arXiv:2507.09264v2 Announce Type: replace Abstract: Transformer-based PDE surrogates achieve remarkable performance but face two key challenges: fixed patch sizes cause systematic error accumulation at harmonic frequencies, and computational costs remain inflexible regardless of problem complexity or available resources. We introduce…
arXiv:2603.04460v1 Announce Type: new Abstract: The quadratic complexity of self-attention during the prefill phase impedes long-context inference in large language models. Existing sparse attention methods face a trade-off among context adaptivity, sampling overhead, and fine-tuning costs. We propose VSPrefill, a…
arXiv:2510.22503v2 Announce Type: replace Abstract: Materials discovery requires navigating vast chemical and structural spaces while satisfying multiple, often conflicting, objectives. We present LLM-guided Evolution for MAterials discovery (LLEMA), a unified framework that couples the scientific knowledge embedded in large language…
arXiv:2603.04461v1 Announce Type: new Abstract: Precipitation nowcasting (short-term forecasting) is still often performed using numerical solvers for physical equations, which are computationally expensive and make limited use of the large volumes of available weather data. Deep learning models have shown…
arXiv:2601.19175v4 Announce Type: replace Abstract: Link sign prediction on a signed graph is a task to determine whether the relationship represented by an edge is positive or negative. Since the presence of negative edges violates the graph homophily assumption that…
arXiv:2603.04464v1 Announce Type: new Abstract: In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand how models process such conflicts,…
arXiv:2602.20396v2 Announce Type: replace Abstract: Explainable artificial intelligence promises to yield insights into relevant features, thereby enabling humans to examine and scrutinize machine learning models or even facilitating scientific discovery. Considering the widespread technique of Shapley values, we find that…
arXiv:2603.04472v1 Announce Type: new Abstract: Accurate predictions of ship trajectories in crowded environments are essential to ensure safety in inland waterways traffic. Recent advances in deep learning promise increased accuracy even for complex scenarios. While the challenge of ship-to-ship awareness…
