arXiv:2603.00181v1 Announce Type: new Abstract: A recent report on “Learning the natural history of human disease with generative transformers” created an opportunity to assess the engineering challenge of delivering user-facing Generative AI applications in privacy-sensitive domains. The application of these…
arXiv:2602.10478v3 Announce Type: replace-cross Abstract: GPU memory errors are a critical threat to deep learning (DL) frameworks, leading to crashes or even security issues. We introduce GPU-Fuzz, a fuzzer locating these issues efficiently by modeling operator parameters as formal constraints.…
arXiv:2603.00190v1 Announce Type: new Abstract: Polysomnography (PSG) provides the gold standard for sleep assessment but suffers from substantial heterogeneity across recording devices and cohorts. There have been growing efforts to build general-purpose foundation models (FMs) for sleep physiology, but lack…
arXiv:2407.08086v2 Announce Type: replace Abstract: Kernels are a fundamental technical primitive in machine learning. In recent years, kernel-based methods such as Gaussian processes are becoming increasingly important in applications where quantifying uncertainty is of key interest. In settings that involve…
arXiv:2603.00191v1 Announce Type: new Abstract: Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing attention in CL. Several LoRA-based CL methods…
arXiv:2502.15483v3 Announce Type: replace Abstract: Deep learning methods for material property prediction have been widely explored to advance materials discovery. However, the prevailing pre-train then fine-tune paradigm often fails to address the inherent diversity and disparity of material tasks. To…
arXiv:2509.21028v3 Announce Type: replace Abstract: We introduce SciTrek, a diagnostic question-answering benchmark designed to probe long-context numerical reasoning in large language models (LLMs). Existing long-context benchmarks mostly focus on simple information retrieval, rely on artificial contexts, or leave numerical reasoning…
arXiv:2603.02002v1 Announce Type: cross Abstract: Foundation MLIPs demonstrate broad applicability across diverse material systems and have emerged as a powerful and transformative paradigm in chemical and computational materials science. Equivariant MLIPs achieve state-of-the-art accuracy in a wide range of benchmarks…
arXiv:2603.02200v1 Announce Type: cross Abstract: The deployment of multimodal models in high-stakes domains, such as self-driving vehicles and medical diagnostics, demands not only strong predictive performance but also reliable mechanisms for detecting failures. In this work, we address the largely…
arXiv:2510.16028v3 Announce Type: replace-cross Abstract: Neural networks increasingly run on hardware outside the user’s control (cloud GPUs, inference marketplaces). Yet ML-as-a-Service reveals little about what actually ran or whether returned outputs faithfully reflect the intended inputs. Users lack recourse against…
