arXiv:2601.08116v3 Announce Type: replace Abstract: Tropical cyclones are among the most consequential weather hazards, yet estimates of their risk are limited by the relatively short historical record. To extend these records, researchers often generate large ensembles of synthetic storms using…
arXiv:2605.03710v1 Announce Type: cross Abstract: Bayesian predictive inference propagates parameter uncertainty to quantities of interest through the posterior-predictive distribution. In practice, this is typically performed using a two-stage procedure: first approximating the posterior distribution of model parameters, and then propagating…
arXiv:2605.03968v1 Announce Type: cross Abstract: Accurate school detection is essential for supporting education initiatives, including infrastructure planning and expanding internet connectivity to underserved areas. However, many regions around the world face challenges due to outdated, incomplete, or unavailable official records.…
arXiv:2605.02935v1 Announce Type: new Abstract: In the era of big data, large-scale machine learning models have revolutionized various fields, driving significant advancements. However, large-scale model training demands high financial and computational resources, which are only affordable by a few technological…
arXiv:2603.00977v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally limited in long-horizon tasks that require structured planning and reliable execution. Existing approaches predominantly rely on flat autoregressive…
arXiv:2605.03820v1 Announce Type: cross Abstract: Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they share a…
arXiv:2605.03441v1 Announce Type: cross Abstract: Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems — using formalisms such as…
arXiv:2605.02937v1 Announce Type: new Abstract: Deep learning in emph{de novo} protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries without explicitly reasoning about which residues or interactions are functionally essential. As a…
arXiv:2605.02914v1 Announce Type: new Abstract: A guard model fine-tuned on entirely benign data can lose all safety alignment — not through adversarial manipulation, but through standard domain specialization. We demonstrate this failure across three purpose-built safety classifiers — LlamaGuard, WildGuard,…
arXiv:2502.04419v3 Announce Type: replace Abstract: Generating synthetic datasets via large language models (LLMs) has emerged as a promising approach to improve LLM performance. However, LLMs inherently reflect biases in their training data, leading to a critical challenge: when models are…
