Real-world machine learning on tabular data relies on complex data preparation pipelines for prediction, data integration, augmentation, and debugging. Designing these pipelines requires substantial domain expertise and engineering effort, motivating the question of how large language models (LLMs) can support tabular ML through code synthesis. We introduce SemPipes, a novel declarative programming model that integrates LLM-powered semantic data operators into tabular ML pipelines. Semantic operators specify data transformations in natural language while delegating execution to a runtime system. […]

Ver mais

arXiv:2602.02596v1 Announce Type: cross Abstract: High dimensional representation drift is commonly quantified using Euclidean or cosine distances, which presuppose fixed coordinates when comparing representations across time, training or preprocessing stages. While effective in many settings, these measures entangle intrinsic changes in the data with variations induced by arbitrary parametrizations. We introduce a projective geometric view of representation drift grounded in the Fubini Study metric, which identifies representations that differ only by gauge transformations such as global rescalings or […]

Ver mais

Although recent studies on time-series anomaly detection have increasingly adopted ever-larger neural network architectures such as transformers and foundation models, they incur high computational costs and memory usage, making them impractical for real-time and resource-constrained scenarios. Moreover, they often fail to demonstrate significant performance gains over simpler methods under rigorous evaluation protocols. In this study, we propose Patch-based representation learning for time-series Anomaly detection (PaAno), a lightweight yet effective method for fast and efficient time-series anomaly detection. PaAno […]

Ver mais

Introduction: The Hidden Cost of Ingestion In a modern data ecosystem, ingestion is often treated as a “background task.” However, as data volumes move into the petabyte scale, the process of moving data from source to “Bronze” and “Silver” layers becomes a massive driver of cloud consumption. As a Digital Healthcare Architect, I’ve observed that most organizations struggle not with storage, but with throughput. If your ingestion pipelines are inefficient, your “Data Freshness” suffers, and your downstream AI […]

Ver mais

arXiv:2602.15112v1 Announce Type: new Abstract: We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper’s repository, we preserve the datasets, evaluation harness, and baseline implementations but withhold the paper’s proposed method. This results in five containerized task environments comprising 39 sub-tasks in total. Within each environment, agents must propose novel hypotheses, run experiments, and attempt […]

Ver mais

arXiv:2601.03315v1 Announce Type: new Abstract: We report a case study of four end-to-end attempts to autonomously generate ML research papers using a pipeline of six LLM agents mapped to stages of the scientific workflow. Of these four, three attempts failed during implementation or evaluation. One completed the pipeline and was accepted to Agents4Science 2025, an experimental inaugural venue that required AI systems as first authors, passing both human and multi-AI review. From these attempts, we document six recurring […]

Ver mais

Glacial Lake Outburst Floods (GLOFs) pose a serious threat in high mountain regions. They are hazardous to communities, infrastructure, and ecosystems further downstream. The classical methods of GLOF detection and prediction have so far mainly relied on hydrological modeling, threshold-based lake monitoring, and manual satellite image analysis. These approaches suffer from several drawbacks: slow updates, reliance on manual labor, and losses in accuracy when clouds interfere and/or lack on-site data. To tackle these challenges, we present IceWatch: a […]

Ver mais

arXiv:2511.01937v2 Announce Type: replace-cross Abstract: Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (RLVR) pipelines filter out “easy” problems for training efficiency, leaving the model to train primarily on harder problems that require longer reasoning chains. This skews the output length distribution upward, resulting in a textbf{model that conflates “thinking longer” with “thinking better”}. In this work, we show that retaining and modestly up-weighting moderately […]

Ver mais

Today the Go team is pleased to release Go 1.25. You can find its binary archives and installers on the download page. Go 1.25 comes with improvements over Go 1.24 across its tools, the runtime, compiler, linker, and the standard library, including the addition of one new package. There are port-specific changes and GODEBUG settings updates. Some of the additions in Go 1.25 are in an experimental stage and become exposed only when you explicitly opt in. Notably, […]

Ver mais