arXiv:2601.10880v1 Announce Type: new Abstract: Promptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct applicability to medical image segmentation remains limited by severe domain shifts, the absence of privileged spatial prompts, and the need to reason over complex anatomical and volumetric structures. Here we present Medical SAM3, a foundation model for universal prompt-driven medical image segmentation, obtained by fully fine-tuning SAM3 on large-scale, heterogeneous 2D and 3D […]

Ver mais

arXiv:2601.15316v1 Announce Type: new Abstract: In recent years, the rapid evolution of large vision-language models (LVLMs) has driven a paradigm shift in multimodal fake news detection (MFND), transforming it from traditional feature-engineering approaches to unified, end-to-end multimodal reasoning frameworks. Early methods primarily relied on shallow fusion techniques to capture correlations between text and images, but they struggled with high-level semantic understanding and complex cross-modal interactions. The emergence of LVLMs has fundamentally changed this landscape by enabling joint modeling […]

Ver mais

arXiv:2602.23565v1 Announce Type: new Abstract: In many economically relevant contexts where machine learning is deployed, multiple platforms obtain data from the same pool of users, each of whom selects the platform that best serves them. Prior work in this setting focuses exclusively on the “local” losses of learners on the distribution of data that they observe. We find that there exist instances where learners who use existing algorithms almost surely converge to models with arbitrarily poor global performance, […]

Ver mais

arXiv:2603.12469v1 Announce Type: new Abstract: Generating precise diagnostic reports from High-Resolution Computed Tomography (HRCT) is critical for clinical workflow, yet it remains a formidable challenge due to the high pathological diversity and spatial sparsity within 3D volumes. While Video Language Models (VideoLMs) have demonstrated remarkable spatio-temporal reasoning in general domains, their adaptability to domain-specific, high-volume medical interpretation remains underexplored. In this work, we present AbSteering, an abnormality-centric framework that steers VideoLMs toward precise HRCT report generation. Specifically, AbSteering […]

Ver mais

arXiv:2505.13370v2 Announce Type: replace-cross Abstract: This paper addresses the growing concern of cascading extreme events, such as an extreme earthquake followed by a tsunami, by presenting a novel method for risk assessment focused on these domino effects. The proposed approach develops an extreme value theory framework within a Kolmogorov-Arnold network (KAN) to estimate the probability of one extreme event triggering another, conditionally on a feature vector. An extra layer is added to the KAN architecture to ensure that […]

Ver mais

arXiv:2604.07405v1 Announce Type: new Abstract: Why does gradient descent reliably find good solutions in non-convex neural network optimization, despite the landscape being NP-hard in the worst case? We show that gradient flow on L-layer ReLU networks without bias preserves L-1 conservation laws C_l = ||W_{l+1}||_F^2 – ||W_l||_F^2, confining trajectories to lower-dimensional manifolds. Under discrete gradient descent, these laws break with total drift scaling as eta^alpha where alpha is approximately 1.1-1.6 depending on architecture, loss function, and width. We […]

Ver mais

Sakana AI’s Digital Red Queen proves that competitive self-play, not supervised learning, may be the real path to artificial general intelligence The Paradigm Shift Hiding in Plain Sight On January 8th, 2025, Sakana AI and Japan’s Ministry of Internal Affairs and Communications published research that fundamentally challenges our assumptions about how machine learning systems acquire capabilities. Their Digital Red Queen (DRQ) algorithm didn’t just achieve superhuman performance in Core War — a Turing-complete programming game from 1984. It demonstrated something far […]

Ver mais

hey everyone, sharing this because it’s directly relevant to what a lot of people here are building. packt publishing is running a hands on workshop on april 25 on context engineering for multi agent systems with denis rothman. what gets covered: – semantic blueprints for multi agent orchestration – MCP integration for standardized agent tool use – context window management across agents – high fidelity RAG pipelines with verifiable citations – safeguards against prompt injection and data poisoning […]

Ver mais

Unsupervised learning of high-dimensional data is challenging due to irrelevant or noisy features obscuring underlying structures. It’s common that only a few features, called the influential features, meaningfully define the clusters. Recovering these influential features is helpful in data interpretation and clustering. We propose i-IF-Learn, an iterative unsupervised framework that jointly performs feature selection and clustering. Our core innovation is an adaptive feature selection statistic that effectively combines pseudo-label supervision with unsupervised signals, dynamically adjusting based on intermediate […]

Ver mais

arXiv:2602.05996v1 Announce Type: cross Abstract: Softmax Self-Attention (SSA) is a key component of Transformer architectures. However, when utilised within skipless architectures, which aim to improve representation learning, recent work has highlighted the inherent instability of SSA due to inducing rank collapse and poorly-conditioned Jacobians. In this work, we design a novel attention mechanism: Orthogonal Self-Attention (OSA), which aims to bypass these issues with SSA, in order to allow for (non-causal) Transformers without skip connections and normalisation layers to […]

Ver mais