arXiv:2408.03459v5 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities but often struggle to align with human preferences, leading to harmful or undesirable outputs. Preference learning, which trains models to distinguish between preferred and non-preferred responses based…
arXiv:2510.12997v1 Announce Type: new Abstract: Test-time scaling has enabled Large Language Models (LLMs) with remarkable reasoning capabilities, particularly in mathematical domains, through intermediate chain-of-thought (CoT) reasoning before generating final answers. However, the specific sources and mechanisms underlying these reasoning capabilities…
arXiv:2504.08821v3 Announce Type: replace Abstract: Active QoS metric prediction, commonly employed in the maintenance and operation of DTN, could enhance network performance regarding latency, throughput, energy consumption, and dependability. Naturally formulated as a multivariate time series forecasting problem, it attracts…
arXiv:2510.12999v1 Announce Type: new Abstract: Time integration of stiff systems is a primary source of computational cost in combustion, hypersonics, and other reactive transport systems. This stiffness can introduce time scales significantly smaller than those associated with other physical processes,…
arXiv:2506.16096v2 Announce Type: replace Abstract: Recent developed graph-based methods for diagnosing brain disorders using functional connectivity highly rely on predefined brain atlases, but overlook the rich information embedded within atlases and the confounding effects of site and phenotype variability. To…
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…
