arXiv:2603.22420v1 Announce Type: new Abstract: Semantic segmentation metrics for 3D point clouds, such as mean Intersection over Union (mIoU) and Overall Accuracy (OA), present two key limitations in the context of aerial LiDAR data. First, they treat all misclassifications equally regardless of their spatial context, overlooking cases where the geometric severity of errors directly impacts the quality of derived geospatial products such as Digital Terrain Models. Second, they are often dominated by the large proportion of easily classified […]

Ver mais

arXiv:2601.14468v1 Announce Type: new Abstract: This paper presents a fractional approximation of the AC optimal power flow (AC OPF) problem based on an all-pass approximation of the exponential power flow kernel. The classical AC OPF relies on trigonometric coupling between bus voltage phasors, which yields a nonconvex program with oscillatory derivatives that can slow, or in some cases destabilize, interior-point methods. We replace the trigonometric terms with an all-pass fractional (APF) approximation whose real and imaginary components act […]

Ver mais

Self-supervised learning (SSL) faces a fundamental conflict between semantic understanding and image reconstruction. High-level semantic SSL (e.g., DINO) relies on global tokens that are forced to be location-invariant for augmentation alignment, a process that inherently discards the spatial coordinates required for reconstruction. Conversely, generative SSL (e.g., MAE) preserves dense feature grids for reconstruction but fails to produce high-level abstractions. We introduce STELLAR, a framework that resolves this tension by factorizing visual features into a low-rank product of semantic […]

Ver mais

arXiv:2603.28902v1 Announce Type: new Abstract: Charts are central to analytical reasoning, yet existing benchmarks for chart understanding focus almost exclusively on single-chart interpretation rather than comparative reasoning across multiple charts. To address this gap, we introduce ChartDiff, the first large-scale benchmark for cross-chart comparative summarization. ChartDiff consists of 8,541 chart pairs spanning diverse data sources, chart types, and visual styles, each annotated with LLM-generated and human-verified summaries describing differences in trends, fluctuations, and anomalies. Using ChartDiff, we evaluate […]

Ver mais

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for Large Language Model (LLM) reasoning, yet current methods face key challenges in resource allocation and policy optimization dynamics: (i) uniform rollout allocation ignores gradient variance heterogeneity across problems, and (ii) the softmax policy structure causes gradient attenuation for high-confidence correct actions, while excessive gradient updates may destabilize training. Therefore, we propose DynaMO, a theoretically-grounded dual-pronged optimization framework. At the sequence level, we prove that uniform allocation is suboptimal […]

Ver mais

arXiv:2602.00972v1 Announce Type: new Abstract: The distributed nature of microservice architecture introduces significant resilience challenges. Traditional testing methods, limited by extensive manual effort and oversimplified test environments, fail to capture production system complexity. To address these limitations, we present Cast, an automated, end-to-end framework for microservice resilience testing in production. It achieves high test fidelity by replaying production traffic against a comprehensive library of application-level faults to exercise internal error-handling logic. To manage the combinatorial test space, Cast […]

Ver mais

People on the orange site are laughing at this, assuming it’s just an ad and that there’s nothing to it. Vulnerability researchers I talk to do not think this is a joke. As an erstwhile vuln researcher myself: do not bet against LLMs on this. Axios: Anthropic’s Claude Opus 4.6 uncovers 500 zero-day flaws in open-source I think vulnerability research might be THE MOST LLM-amenable software engineering problem. Pattern-driven. Huge corpus of operational public patterns. Closed loops. Forward […]

Ver mais

I did not start my career thinking deeply about regulation. Like most tech-focused product managers, I cared about velocity, user experience, system reliability and scale. That instinct served me well—until I began leading platforms that moved money, made credit decisions and carried long-term financial consequences for customers. Regulation did not show up as paperwork, it showed up as questions the system would eventually be forced to answer. Regulation Is Delayed Interrogation I learned quickly that in banking, regulation […]

Ver mais

arXiv:2604.00947v1 Announce Type: cross Abstract: Since the random language model was proposed by E. DeGiuli [Phys. Rev. Lett. 122, 128301], language models have been investigated intensively from the viewpoint of statistical mechanics. Recently, the existence of a Berezinskii–Kosterlitz–Thouless transition was numerically demonstrated in models with long-range interactions between symbols. In statistical mechanics, it has long been known that long-range interactions can induce phase transitions. Therefore, it has remained unclear whether phase transitions observed in language models originate from […]

Ver mais

arXiv:2603.00688v1 Announce Type: new Abstract: Reading has always been an integral part of both professional and personal life. Character and layout recognition and understanding by computers are well-explored areas. Nevertheless, how characters and layout are read and perceived by humans remains relatively underexplored. This work contributes to the field of human-document interaction (HDI) by investigating the effects of character and layout personalization on readability. The paper presents an empirical study on how parts-of-speech (POS)-based character and layout modifications […]

Ver mais