arXiv:2510.02340v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely used for temporal prediction, but their reliance on pretraining data raises contamination concerns, as accurate predictions on pre-cutoff test data may reflect memorization rather than reasoning, leading to an…
arXiv:2510.13050v1 Announce Type: new Abstract: Precipitation nowcasting, which predicts rainfall up to a few hours ahead, is a critical tool for vulnerable communities in the Global South frequently exposed to intense, rapidly developing storms. Timely forecasts provide a crucial window…
arXiv:2510.13697v1 Announce Type: cross Abstract: Repository-level pretraining is commonly used to enable large language models for code to leverage codebase-wide context. This enhances their ability to generate accurate and context-aware code completions. In this work, we investigate how different repository-processing…
arXiv:2510.13052v1 Announce Type: new Abstract: Classical optimization theory deals with fixed, time-invariant objective functions. However, time-varying optimization has emerged as an important subject for decision-making in dynamic environments. In this work, we study the problem of learning from streaming data…
arXiv:2510.13763v1 Announce Type: cross Abstract: Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging modern generative methods like diffusion models to map observed data to model parameters or…
After being trained with this technique, vision-language models can better identify a unique item in a new scene.
arXiv:2510.08141v3 Announce Type: replace Abstract: Reinforcement fine-tuning (RFT) is essential for enhancing the reasoning capabilities of large language models (LLM), yet the widely adopted Group Relative Policy Optimization (GRPO) suffers from entropy collapse, where entropy monotonically decreases, exploration vanishes, and…
arXiv:2411.15557v4 Announce Type: replace-cross Abstract: Unsupervised domain adaptation remains a critical challenge in enabling the knowledge transfer of models across unseen domains. Existing methods struggle to balance the need for domain-invariant representations with preserving domain-specific features, which is often due…
arXiv:2506.02897v2 Announce Type: replace Abstract: Federated Learning (FL) enables privacy-preserving collaborative model training, but its effectiveness is often limited by client data heterogeneity. We introduce a client-selection algorithm that (i) dynamically forms nonoverlapping coalitions of clients based on asymptotic agreement…
arXiv:2209.02935v5 Announce Type: replace Abstract: There is no, nor will there ever be, single best clustering algorithm. Nevertheless, we would still like to be able to distinguish between methods that work well on certain task types and those that systematically…
