arXiv:2509.02661v3 Announce Type: replace-cross Abstract: This community paper developed out of the NSF Workshop on the Future of Artificial Intelligence (AI) and the Mathematical and Physics Sciences (MPS), which was held in March 2025 with the goal of understanding how the MPS domains (Astronomy, Chemistry, Materials Research, Mathematical Sciences, and Physics) can best capitalize on, and contribute to, the future of AI. We present here a summary and snapshot of the MPS community’s perspective, as of Spring/Summer 2025, […]

Ver mais

Recent advances in large language models (LLMs) have enabled the development of multimodal medical AI. While models such as MedGemini achieve high accuracy on VQA tasks like USMLE MM, their performance on ECG based tasks remains limited, and some models, such as MedGemma, do not support ECG data at all. Interpreting ECGs is inherently challenging, and diagnostic accuracy can vary depending on the interpreter’s experience. Although echocardiography provides rich diagnostic information, it requires specialized equipment and personnel, limiting […]

Ver mais

When using Crossplane to provision Azure resources from Kubernetes, authentication becomes a critical challenge. Traditional approaches using service principal secrets are insecure and operationally complex. This blog post shares how we solved Azure authentication using Workload Identity Federation across three distinct deployment scenarios: Local Development: Kind cluster with Crossplane on developer laptops CI/CD Pipeline: GitHub Actions running Kind cluster with Crossplane for automated testing Production: EKS cluster with Crossplane managing Azure infrastructure Each scenario presented unique challenges, and […]

Ver mais

Sampling efficiency is a key bottleneck in reinforcement learning with verifiable rewards. Existing group-based policy optimization methods, such as GRPO, allocate a fixed number of rollouts for all training prompts. This uniform allocation implicitly treats all prompts as equally informative, and could lead to inefficient computational budget usage and impede training progress. We introduce Ours, a Variance-Informed Predictive allocation strategy that allocates a given rollout budget to the prompts in the incumbent batch to minimize the expected gradient […]

Ver mais

arXiv:2312.17111v2 Announce Type: replace Abstract: Contemporary applications, such as recommendation systems and mobile health monitoring, require real-time processing and analysis of sequentially arriving high-dimensional tensor data. Traditional offline learning, involving the storage and utilization of all data in each computational iteration, becomes impractical for these tasks. Furthermore, existing low-rank tensor methods lack the capability for online statistical inference, which is essential for real-time predictions and informed decision-making. This paper addresses these challenges by introducing a novel online inference […]

Ver mais

arXiv:2208.14960v5 Announce Type: replace-cross Abstract: Gaussian processes are arguably the most important class of spatiotemporal models within machine learning. They encode prior information about the modeled function and can be used for exact or approximate Bayesian learning. In many applications, particularly in physical sciences and engineering, but also in areas such as geostatistics and neuroscience, invariance to symmetries is one of the most fundamental forms of prior information one can consider. The invariance of a Gaussian process’ covariance […]

Ver mais

arXiv:2603.10074v1 Announce Type: new Abstract: We construct a minimal task that isolates conditional learning in neural networks: a surjective map with K-fold ambiguity, resolved by a selector token z, so H(A | B) = log K while H(A | B, z) = 0. The model learns the marginal P(A | B) first, producing a plateau at exactly log K, before acquiring the full conditional in a sharp, collective transition. The plateau has a clean decomposition: height = log […]

Ver mais

Retrieval-augmented generation (RAG) is widely used to ground Large Language Models (LLMs) for multi-hop question answering. Recent work mainly focused on improving answer accuracy via fine-tuning and structured or reinforcement-based optimization. However, reliable reasoning in response generation faces three challenges: 1) Reasoning Collapse. Reasoning in multi-hop QA is inherently complex due to multi-hop composition and is further destabilized by noisy retrieval. 2) Reasoning-answer inconsistency. Due to the intrinsic uncertainty of LLM generation and exposure to evidence–distractor mixtures, models […]

Ver mais

arXiv:2601.04336v1 Announce Type: new Abstract: The emergence of generative AI (GAI) has sparked diverse opinions regarding its appropriate use across various domains, including education. This pilot study investigates university students’ perceptions of GAI in higher education classrooms, aiming to lay the groundwork for understanding these attitudes. With a participation rate of approximately 4.4%, the study highlights the challenges of engaging students in GAI-related research and underscores the need for larger sample sizes in future studies. By gaining insights […]

Ver mais

Accurate traffic flow prediction remains a fundamental challenge in intelligent transportation systems, particularly in cross-domain, data-scarce scenarios where limited historical data hinders model training and generalisation. The complex spatio-temporal dependencies and nonlinear dynamics of urban mobility networks further complicate few-shot learning across different cities. This paper proposes MCPST, a novel Multi-phase Consensus Spatio-Temporal framework for few-shot traffic forecasting that reconceptualises traffic prediction as a multi-phase consensus learning problem. Our framework introduces three core innovations: (1) a multi-phase engine […]

Ver mais