arXiv:2604.11835v2 Announce Type: replace Abstract: Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine, where electronic…
arXiv:2605.02765v1 Announce Type: cross Abstract: LLMs are increasingly used for end-user task planning, yet their black-box nature limits users’ ability to ensure reliability and control. While recent systems incorporate verification techniques, it remains unclear how users can effectively apply such…
arXiv:2507.15774v2 Announce Type: replace Abstract: While deep learning is facing an homogenization across modalities led by Transformers, they are still challenged by shallow linear models in the time-series forecasting task. Our hypothesis is that models should learn a direct link…
arXiv:2605.01882v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown considerable potential in chart understanding and reasoning tasks. However, they still struggle with high information density (HID) charts characterized by multiple subplots, legends, and dense annotations due to…
arXiv:2605.02318v1 Announce Type: cross Abstract: In 2011, Judea Pearl received the Turing Award, considered the Nobel Prize in Computing, for fundamental contributions to artificial intelligence through the development of a calculus for probabilistic and causal reasoning. It includes pioneering the…
arXiv:2605.00925v1 Announce Type: new Abstract: Integrating molecular, morphological, and clinical data is essential for basic and translational biomedical research, yet systematic frameworks for jointly modeling these modalities remain limited. Here we present Haiku, a tri-modal contrastive learning model trained on…
arXiv:2605.00926v1 Announce Type: new Abstract: The Receiver Operating Characteristic (ROC) curve of a binary classifier has often been utilized to measure the performance of the classifier. The area beneath this curve is used in particular because of its quoted probabilistic…
arXiv:2605.00876v1 Announce Type: new Abstract: Vision-language models (VLMs) read an image and produce text in a single forward pass, whereas radiologists typically inspect an image several times and consult the literature before writing a report. We introduce GAZE (Grounded Agentic…
arXiv:2605.00924v1 Announce Type: new Abstract: AI-generated content (AIGC) detectors are increasingly deployed in high-stakes settings such as academic integrity screening, yet their reliability rests on a fundamental paradox: as language models are trained on human-written corpora, the statistical boundary between…
arXiv:2605.00837v1 Announce Type: new Abstract: Entropic regularized optimal transport (OT) via the Sinkhorn algorithm has become a fundamental tool in machine learning, yet existing implementations either suffer from numerical instability for small regularization parameters or incur significant overhead from deep…
