arXiv:2602.04886v1 Announce Type: cross Abstract: Normative modeling estimates reference distributions of biological measures conditional on covariates, enabling centiles and clinically interpretable deviation scores to be derived. Most neuroimaging pipelines fit one model per imaging-derived phenotype (IDP), which scales well but discards multivariate dependence that may encode coordinated patterns. We propose denoising diffusion probabilistic models (DDPMs) as a unified conditional density estimator for tabular IDPs, from which univariate centiles and deviation scores are derived by sampling. We utilise two […]

Ver mais

arXiv:2603.00687v1 Announce Type: new Abstract: Noise and artifacts during computed tomography (CT) scans are a fundamental challenge affecting disease diagnosis. However, current methods either involve excessively long reconstruction times or rely on data-driven models for optimization, failing to adequately consider the valuable information inherent in the data itself, especially medical 3D data. This work proposes a reconstruction method under ultra-low raw data conditions, requiring no external data and avoiding lengthy pre-training processes. By leveraging spatial nonlocal similarity and […]

Ver mais

arXiv:2403.01673v2 Announce Type: replace Abstract: For Multivariate Time Series Forecasting (MTSF), recent deep learning applications show that univariate models frequently outperform multivariate ones. To address the difficiency in multivariate models, we introduce a method to Construct Auxiliary Time Series (CATS) that functions like a 2D temporal-contextual attention mechanism, which generates Auxiliary Time Series (ATS) from Original Time Series (OTS) to effectively represent and incorporate inter-series relationships for forecasting. Key principles of ATS – continuity, sparsity, and variability – […]

Ver mais

I’m trying to understand the exact logic behind this key step in dynamic programming. We know that V* satisfies the Bellman optimality equation: V*(s) = max_a [ r(s,a) + γ Σ_{s’} P(s’|s,a) V*(s’) ] Now define the greedy policy with respect to V*: a*(s) = argmax_a [ r(s,a) + γ Σ_{s’} P(s’|s,a) V*(s’) ] and define the deterministic policy: π*(a|s) = 1 if a = a*(s) 0 otherwise Step 1: Plug greedy action into Bellman optimality Because π* […]

Ver mais

arXiv:2508.11847v3 Announce Type: replace Abstract: We propose a method for evaluating the robustness of widely used LLM ranking systems — variants of a Bradley–Terry model — to dropping a worst-case very small fraction of preference data. Our approach is computationally fast and easy to adopt. When we apply our method to matchups from popular LLM ranking platforms, including Chatbot Arena and derivatives, we find that the rankings of top-performing models can be remarkably sensitive to the removal of […]

Ver mais

arXiv:2602.02537v1 Announce Type: new Abstract: We introduce WorldVQA, a benchmark designed to evaluate the atomic visual world knowledge of Multimodal Large Language Models (MLLMs). Unlike current evaluations, which often conflate visual knowledge retrieval with reasoning, WorldVQA decouples these capabilities to strictly measure “what the model memorizes.” The benchmark assesses the atomic capability of grounding and naming visual entities across a stratified taxonomy, spanning from common head-class objects to long-tail rarities. We expect WorldVQA to serve as a rigorous […]

Ver mais

Multimodal generative models have demonstrated remarkable capabilities in visual understanding, audio synthesis, and embodied control. Such capabilities, however, come with substantial inference overhead due to autoregressive decoding or iterative generation processes, compounded by modality-specific challenges including extensive visual token redundancy, strict real-time latency in robotic control, and prolonged sequential generation in text-to-image synthesis. Speculative decoding has emerged as a promising paradigm to accelerate inference without degrading output quality, yet existing surveys remain focused on text-only large language models. […]

Ver mais

arXiv:2602.04031v1 Announce Type: new Abstract: Tabular Language Models (TLMs) have been claimed to achieve emergent generalization for tabular prediction. We conduct a systematic re-evaluation of Tabula-8B as a representative TLM, utilizing 165 datasets from the UniPredict benchmark. Our investigation reveals three findings. First, binary and categorical classification achieve near-zero median lift over majority-class baselines and strong aggregate performance is driven entirely by quartile classification tasks. Second, top-performing datasets exhibit pervasive contamination, including complete train-test overlap and task-level leakage […]

Ver mais

Jürgen Schmidhuber shares his insights on the evolution and future of AI. He discusses the development of self-improving AI systems, the concept of artificial curiosity, and the potential for machines to achieve creativity akin to humans. Schmidhuber also explores the implications of advanced AI on society, emphasizing the importance of aligning AI goals with human values to ensure beneficial outcomes. He envisions a future where AI contributes positively to various fields, including science, art, and technology.

Ver mais