arXiv:2602.21265v1 Announce Type: new Abstract: We introduce ToolMATH, a math-grounded benchmark that evaluates tool-augmented language models in realistic multi-tool environments where the output depends on calling schema-specified tools and sustaining multi-step execution. It turns math problems into a controlled, correctness-checkable benchmark with tool sets, enabling systematic evaluation of model reliability under (1) large, overlapping tool catalogs and (2) the absence of the intended capability. ToolMATH provides actionable diagnostic evidence of failure modes in tool-augmented agents, helping identify the […]

Ver mais

arXiv:2504.06477v2 Announce Type: replace Abstract: Sparse learning is ubiquitous in many machine learning tasks. It aims to regularize the goodness-of-fit objective by adding a penalty term to encode structural constraints on the model parameters. In this paper, we develop a flexible sparse learning framework tailored to high-dimensional heavy-tailed locally stationary time series (LSTS). The data-generating mechanism incorporates a regression function that changes smoothly over time and is observed under noise belonging to the class of sub-Weibull and regularly […]

Ver mais

arXiv:2602.20399v1 Announce Type: new Abstract: Neural simulators promise efficient surrogates for physics simulation, but scaling them is bottlenecked by the prohibitive cost of generating high-fidelity training data. Pre-training on abundant off-the-shelf geometries offers a natural alternative, yet faces a fundamental gap: supervision on static geometry alone ignores dynamics and can lead to negative transfer on physics tasks. We present GeoPT, a unified pre-trained model for general physics simulation based on lifted geometric pre-training. The core idea is to […]

Ver mais

Table of Links Abstract and 1. Introduction Some recent trends in theoretical ML 2.1 Deep Learning via continuous-time controlled dynamical system 2.2 Probabilistic modeling and inference in DL 2.3 Deep Learning in non-Euclidean spaces 2.4 Physics Informed ML Kuramoto model 3.1 Kuramoto models from the geometric point of view 3.2 Hyperbolic geometry of Kuramoto ensembles 3.3 Kuramoto models with several globally coupled sub-ensembles Kuramoto models on higher-dimensional manifolds 4.1 Non-Abelian Kuramoto models on Lie groups 4.2 Kuramoto models […]

Ver mais

Claude can code, but can it check binary executables? We already did our experiments with using NSA software to hack a classic Atari game. This time, we want to focus on a much more practical task — using AI agents for malware detection. We partnered with Michał “Redford” Kowalczyk,a reverse engineering expert from Dragon Sector, known for finding malicious code in Polish trains, to create a benchmark of finding backdoors in binary executables, without access to source code. […]

Ver mais

The A.I. Disruption We’ve Been Waiting for Has Arrived New opinion piece from Paul Ford in the New York Times. Unsurprisingly for a piece by Paul it’s packed with quoteworthy snippets, but a few stood out for me in particular. Paul describes the November moment that so many other programmers have observed, and highlights Claude Code’s ability to revive old side projects: [Claude Code] was always a helpful coding assistant, but in November it suddenly got much better, […]

Ver mais

arXiv:2603.00602v1 Announce Type: new Abstract: Detecting out-of-distribution (OOD) graphs is crucial for ensuring the safety and reliability of Graph Neural Networks. In unsupervised graph-level OOD detection, models are typically trained using only in-distribution (ID) data, resulting in incomplete feature space characterization and weak decision boundaries. Although synthesizing outliers offers a promising solution, existing approaches rely on fixed, non-adaptive sampling heuristics (e.g., distance- or density-based), limiting their ability to explore informative OOD regions. We propose a Policy-Guided Outlier Synthesis […]

Ver mais

Mistral’s new speech model can run on a smartwatch or a smartphone.

Ver mais

We built a Label Quality Score (LQS) system for our dataset marketplace and opened it up as a free standalone tool. Upload a dataset → get a 0–100 score broken down across 7 dimensions with specific flags for what’s degrading quality. Supports CSV, Parquet, JSONL, COCO JSON, YOLO — most common ML formats. Link: labelsets.ai/quality-audit Not trying to pitch anything, genuinely want to know if the scoring makes sense to people who work with datasets professionally. Happy to […]

Ver mais