arXiv:2510.10921v2 Announce Type: replace-cross Abstract: Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP perform well on global alignment, they often…
arXiv:2510.15076v1 Announce Type: new Abstract: The $ell_p$-norm objectives for correlation clustering present a fundamental trade-off between minimizing total disagreements (the $ell_1$-norm) and ensuring fairness to individual nodes (the $ell_infty$-norm). Surprisingly, in the offline setting it is possible to simultaneously approximate…
arXiv:2510.15786v1 Announce Type: cross Abstract: We present DexCanvas, a large-scale hybrid real-synthetic human manipulation dataset containing 7,000 hours of dexterous hand-object interactions seeded from 70 hours of real human demonstrations, organized across 21 fundamental manipulation types based on the Cutkosky…
arXiv:2510.15101v1 Announce Type: new Abstract: Forecasting high-dimensional, PDE-governed dynamics remains a core challenge for generative modeling. Existing autoregressive and diffusion-based approaches often suffer cumulative errors and discretisation artifacts that limit long, physically consistent forecasts. Flow matching offers a natural alternative,…
arXiv:2501.19018v3 Announce Type: replace Abstract: The Tsetlin Machine (TM) architecture has recently demonstrated effectiveness in Machine Learning (ML), particularly within Natural Language Processing (NLP). It has been utilized to construct word embedding using conjunctive propositional clauses, thereby significantly enhancing our…
arXiv:2510.15110v1 Announce Type: new Abstract: Reasoning language models such as OpenAI-o1, DeepSeek-R1, and Qwen achieve strong performance via extended chains of thought but often generate unnecessarily long outputs. Maximizing intelligence per token–accuracy relative to response length–remains an open problem. We…
arXiv:2505.23606v3 Announce Type: replace Abstract: Unified generation models aim to handle diverse tasks across modalities — such as text generation, image generation, and vision-language reasoning — within a single architecture and decoding paradigm. Autoregressive unified models suffer from slow inference…
arXiv:2510.15127v1 Announce Type: new Abstract: Identifying the effects of mechanical ventilation strategies and protocols in critical care requires analyzing data from heterogeneous patient-ventilator systems within the context of the clinical decision-making environment. This research develops a framework to help understand…
arXiv:2508.21785v2 Announce Type: replace Abstract: Heart rate prediction is vital for personalized health monitoring and fitness, while it frequently faces a critical challenge when deploying in real-world: data heterogeneity. We classify it in two key dimensions: source heterogeneity from fragmented…
arXiv:2510.15132v1 Announce Type: new Abstract: We study nonparametric estimation of a probability mass function (PMF) on a large discrete support, where the PMF is multi-modal and heavy-tailed. The core idea is to treat the empirical PMF as a signal on…
