arXiv:2510.03262v1 Announce Type: new Abstract: We propose Orthogonal Monte Carlo Dropout, a mechanism that enforces strict orthogonality when combining sparse semantic vectors without extra time complexity. LoRA, a popular fine-tuning method for large models, typically trains a module to represent…
arXiv:2507.08870v2 Announce Type: replace Abstract: The field of AI research is advancing at an unprecedented pace, enabling automated hypothesis generation and experimental design across diverse domains such as biology, mathematics, and artificial intelligence. Despite these advancements, there remains a significant…
arXiv:2510.03263v1 Announce Type: new Abstract: The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawful content. This has accelerated the push for machine…
arXiv:2510.00384v2 Announce Type: replace Abstract: We propose the multistep port-Hamiltonian Gaussian process (MS-PHS GP) to learn physically consistent continuous-time dynamics and a posterior over the Hamiltonian from noisy, irregularly-sampled trajectories. By placing a GP prior on the Hamiltonian surface $H$…
arXiv:2510.03264v1 Announce Type: new Abstract: The prevailing paradigm for enhancing the reasoning abilities of LLMs revolves around post-training on high-quality, reasoning-intensive data. While emerging literature suggests that reasoning data is increasingly incorporated also during the mid-training stage-a practice that is…
arXiv:2410.23066v2 Announce Type: replace-cross Abstract: State-of-the-art Extreme Multi-Label Text Classification models rely on multi-label attention to focus on key tokens in input text, but learning good attention weights is challenging. We introduce PLANT – Pretrained and Leveraged Attention – a…
arXiv:2510.03265v1 Announce Type: new Abstract: Large-scale foundation models demonstrate strong performance across language, vision, and reasoning tasks. However, how they internally structure and stabilize concepts remains elusive. Inspired by causal inference, we introduce the MindCraft framework built upon Concept Trees.…
arXiv:2505.17101v3 Announce Type: replace-cross Abstract: Deep neural networks are known to develop similar representations for semantically related data, even when they belong to different domains, such as an image and its description, or the same text in different languages. We…
arXiv:2510.03266v1 Announce Type: new Abstract: Climate anomalies significantly impact terrestrial carbon cycle dynamics, necessitating robust methods for detecting and analyzing anomalous behavior in plant productivity. This study presents a novel application of variational autoencoders (VAE) for identifying extreme events in…
arXiv:2509.11465v2 Announce Type: replace-cross Abstract: We introduce CEMTM, a context-enhanced multimodal topic model designed to infer coherent and interpretable topic structures from both short and long documents containing text and images. CEMTM builds on fine-tuned large vision language models (LVLMs)…
