arXiv:2602.02615v1 Announce Type: new Abstract: Existing Byzantine robust aggregation mechanisms typically rely on fulldimensional gradi ent comparisons or pairwise distance computations, resulting in computational overhead that limits applicability in large scale and resource constrained federated systems. This paper proposes TinyGuard, a lightweight Byzantine defense that augments the standard FedAvg algorithm via statistical update f ingerprinting. Instead of operating directly on high-dimensional gradients, TinyGuard extracts compact statistical fingerprints cap turing key behavioral properties of client updates, including norm statistics, […]

Ver mais

While standard reinforcement learning optimizes a single reward signal, many applications require optimizing a nonlinear utility $f(J_1^π,dots,J_M^π)$ over multiple objectives, where each $J_m^π$ denotes the expected discounted return of a distinct reward function. A common approach is concave scalarization, which captures important trade-offs such as fairness and risk sensitivity. However, nonlinear scalarization introduces a fundamental challenge for policy gradient methods: the gradient depends on $partial f(J^π)$, while in practice only empirical return estimates $hat J$ are available. Because […]

Ver mais

arXiv:2602.07065v1 Announce Type: new Abstract: Contactless and non-invasive estimation of mechanical properties of physical media from optical observations is of interest for manifold engineering and biomedical applications, where direct physical measurements are not possible. Conventional approaches to the assessment of image displacement and non-contact material probing typically rely on time-consuming iterative algorithms for non-rigid image registration and constitutive modelling using discretization and iterative numerical solving techniques, such as Finite Element Method (FEM) and Finite Difference Method (FDM), which […]

Ver mais

arXiv:2604.09782v1 Announce Type: new Abstract: Chagas disease screening via ECGs is limited by scarce and noisy labels in existing datasets. We propose a biomarker-based pretraining approach, where an ECG feature extractor is first trained to predict percentile-binned blood biomarkers from the MIMIC-IV-ECG dataset. The pretrained model is then fine-tuned on Brazilian datasets for Chagas detection. Our 5-model ensemble, developed by the Ahus AIM team, achieved a challenge score of 0.269 on the hidden test set, ranking 5th in […]

Ver mais

For minimally rigid graphs, the same edge-length data can admit multiple realizations (up to translations and rotations). Finding graphs with exceptionally many realizations is an extremal problem in rigidity theory, but exhaustive search quickly becomes infeasible due to the super-exponential growth of the number of candidate graphs and the high cost of realization-count evaluation. We propose a reinforcement-learning approach that constructs minimally rigid graphs via 0- and 1-extensions, also known as Henneberg moves. We optimize realization-count invariants using […]

Ver mais

arXiv:2508.21022v2 Announce Type: replace-cross Abstract: Subsampled natural gradient descent (SNG) has been used to enable high-precision scientific machine learning, but standard analyses based on stochastic preconditioning fail to provide insight into realistic small-sample settings. We overcome this limitation by instead analyzing SNG as a sketch-and-project method. Motivated by this lens, we discard the usual theoretical proxy which decouples gradients and preconditioners using two independent mini-batches, and we replace it with a new proxy based on squared volume sampling. […]

Ver mais

I gave my OpenClaw AI agent the name Aris, access to my health data, family Telegram chat, calendar, and GitHub. OpenClaw is an open-source agent framework for building and running personal AI assistants that can interact with various apps and data sources. Simon Willison would call this insane, and he is probably right. Here’s what a Tuesday morning looks like. At 7:30, Aris sends my morning briefing: sleep score from Apple Watch, resting heart rate trending up, recovery […]

Ver mais

As Large Language Models (LLMs) achieve remarkable empirical success through scaling model and data size, pretraining has become increasingly critical yet computationally prohibitive, hindering rapid development. Despite the availability of numerous pretrained LLMs developed at significant computational expense, a fundamental real-world question remains underexplored: textit{Can we leverage existing small pretrained models to accelerate the training of larger models?} In this paper, we propose a Late-to-Early Training (LET) paradigm that enables LLMs to explicitly learn later knowledge in earlier […]

Ver mais

As cryptocurrency adoption accelerates globally, the gap between traditional finance and Web3 remains one of the industry’s most persistent challenges. While blockchain infrastructure has matured dramatically, the simple act of converting fiat to crypto and back continues to create friction for millions of users and businesses. Ramp Network has spent eight years addressing this fundamental problem, building the financial pipes that connect 150+ countries to the crypto economy. In this interview, we sit down with Przemek Kowalczyk, co-founder […]

Ver mais