digitado

arXiv:2603.25823v1 Announce Type: new Abstract: Beneath the stunning visual fidelity of modern AIGC models lies a “logical desert”, where systems fail tasks that require physical, causal, or complex spatial reasoning. Current evaluations largely rely on superficial metrics or fragmented benchmarks, creating a “performance mirage” that overlooks the generative process. To address this, we introduce ViGoR Vision-G}nerative Reasoning-centric Benchmark), a unified framework designed to dismantle this mirage. ViGoR distinguishes itself through four key innovations: 1) holistic cross-modal coverage bridging […]

Ver mais

arXiv:2603.25821v1 Announce Type: new Abstract: We present Doctorina MedBench, a comprehensive evaluation framework for agent-based medical AI based on the simulation of realistic physician-patient interactions. Unlike traditional medical benchmarks that rely on solving standardized test questions, the proposed approach models a multi-step clinical dialogue in which either a physician or an AI system must collect medical history, analyze attached materials (including laboratory reports, images, and medical documents), formulate differential diagnoses, and provide personalized recommendations. System performance is evaluated […]

Ver mais

arXiv:2603.25819v1 Announce Type: new Abstract: Cross-view geo-spatial learning consists of two important tasks: Cross-View Geo-Localization (CVGL) and Cross-View Image Synthesis (CVIS), both of which rely on establishing geometric correspondences between ground and aerial views. Recent Geometric Foundation Models (GFMs) have demonstrated strong capabilities in extracting generalizable 3D geometric features from images, but their potential in cross-view geo-spatial tasks remains underexplored. In this work, we present Geo^2, a unified framework that leverages Geometric priors from GFMs (e.g., VGGT) to […]

Ver mais

arXiv:2603.25816v1 Announce Type: new Abstract: Reach-avoid analysis is fundamental to reasoning about the safety and goal-reaching behavior of dynamical systems, and serves as a foundation for specifying and verifying more complex control objectives. This paper introduces a reach-avoid certificate framework for discrete-time, continuous-space stochastic systems over both finite- and infinite-horizon settings. We propose two formulations: time-varying and time-invariant certificates. We also show how these certificates can be synthesized using sum-of-squares (SOS) optimization, providing a convex formulation for verifying […]

Ver mais

arXiv:2603.25813v1 Announce Type: new Abstract: We present MAGNET (Model Autonomously Growing Network), a decentralized system for autonomous generation, training, and serving of domain-expert language models across commodity hardware. MAGNET integrates four components: (1) autoresearch, an autonomous ML research pipeline that automates dataset generation, hyperparameter exploration, evaluation, and error-driven iteration; (2) BitNet b1.58 ternary training, enabling CPU-native inference via bitnet.cpp without GPU hardware; (3) DiLoCo-based distributed merging for communication-efficient aggregation of domain specialists; and (4) on-chain contribution tracking on […]

Ver mais

arXiv:2603.25811v1 Announce Type: new Abstract: One of the biggest challenges of value-based decision-making is dealing with the subjective nature of values. The relative importance of a value for a particular decision varies between individuals, and people may also have different interpretations of what aligning with a value means in a given situation. While members of a society are likely to share a set of principles or values, their value systems–that is, how they interpret these values and the […]

Ver mais

arXiv:2603.25810v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown promising results in automating formal verification. However, existing approaches treat proof generation as a static, end-to-end prediction over source code, relying on limited verifier feedback and lacking access to concrete program behaviors. We present EXVERUS, a counterexample-guided framework that enables LLMs to reason about proofs using behavioral feedback via counterexamples. When a proof fails, EXVERUS automatically generates and validates counterexamples, and then guides the LLM to generalize […]

Ver mais

arXiv:2603.25804v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualizations from real-world data remains largely unassessed. To address this gap, we introduce textbf{texttt{RealChart2Code}}, a new large-scale benchmark with over 2,800 instances grounded in authentic datasets and featuring tasks with clear analytical intent. Crucially, it is the first benchmark to systematically evaluate chart generation from large-scale raw data and assess iterative code refinement […]

Ver mais

arXiv:2603.25803v1 Announce Type: new Abstract: Training Vision Transformers (ViTs) presents significant challenges, one of which is the emergence of artifacts in attention maps, hindering their interpretability. Darcet et al. (2024) investigated this phenomenon and attributed it to the need of ViTs to store global information beyond the [CLS] token. They proposed a novel solution involving the addition of empty input tokens, named registers, which successfully eliminate artifacts and improve the clarity of attention maps. In this work, we […]

Ver mais

arXiv:2603.25802v1 Announce Type: new Abstract: Computational pathology relies on effective representation learning to support cancer research and precision medicine. Although self-supervised learning has driven major progress at the patch and whole-slide image levels, representation learning at the single-cell level remains comparatively underexplored, despite its importance for characterizing cell types and cellular phenotypes. We introduce LEMON (Learning Embeddings from Morphology Of Nuclei), a self-supervised foundation model for scalable single-cell image representation learning. Trained on millions of cell images from […]

Ver mais