This is the first dev snapshot for 4.4! During the beta and release candidate stages of 4.3, we accumulated a lot of PRs that were of great quality, but deemed too risky to include in 4.3. We have begun merging those PRs now and have quickly gathered a lot of changes that warrant a dev release! Many of the changes in this release are bug fixes that will be backported to Godot 4.3 and released in 4.3.1! So […]

Ver mais

arXiv:2310.11736v4 Announce Type: replace-cross Abstract: We study feature learning in a compositional variant of kernel ridge regression in which the predictor is applied to a learnable linear transformation of the input. When the response depends on the input only through a low-dimensional predictive subspace, we show that all global minimizers of the population objective for the linear transformation annihilate directions orthogonal to this subspace, and in certain regimes, exactly identify the subspace. Moreover, we show that global minimizers […]

Ver mais

arXiv:2512.17632v2 Announce Type: replace Abstract: High-dimensional covariance estimation is notoriously sensitive to outliers. While statistically optimal estimators exist for general heavy-tailed distributions, they often rely on computationally expensive techniques like semidefinite programming or iterative M-estimation ($O(d^3)$). In this work, we target the specific regime of textbf{Sub-Weibull distributions} (characterized by stretched exponential tails $exp(-t^alpha)$). We investigate a computationally efficient alternative: the textbf{Cross-Fitted Norm-Truncated Estimator}. Unlike element-wise truncation, our approach preserves the spectral geometry while requiring $O(Nd^2)$ operations, which represents […]

Ver mais

Google is moving more into your personal territory with its AI Mode using Personal Intelligence. For the uninitiated, Personal Intelligence is an opt-in feature that Google introduced earlier this month, which lets Gemini get access to your personal data across Google apps like Gmail, Google Photos, and more, to provide contextual and proactive assistance. Putting it simply, this feature lets Gemini answer your queries and offer real-time recommendations based on specific information from inside Google apps. Personal Intelligence […]

Ver mais

arXiv:2602.10329v1 Announce Type: new Abstract: Human reasoning is shaped by resource rationality — optimizing performance under constraints. Recently, inference-time scaling has emerged as a powerful paradigm to improve the reasoning performance of Large Language Models by expanding test-time computation. Specifically, instruction-tuned (IT) models explicitly generate long reasoning steps during inference, whereas Large Reasoning Models (LRMs) are trained by reinforcement learning to discover reasoning paths that maximize accuracy. However, it remains unclear whether resource-rationality can emerge from such scaling […]

Ver mais

Model adaptation to production environment is critical for reliable Machine Learning Operations (MLOps), less attention is paid to developing systematic framework for updating the ML models when they fail under data drift. This paper compares the transfer learning enabled model update strategies including ensemble transfer learning (ETL), all-layers transfer learning (ALTL), and last-layer transfer learning (LLTL) for updating the failed feedforward artificial neural network (ANN) model. The flue gas differential pressure across the air preheater unit installed in […]

Ver mais

Direct preference optimization (DPO) is an effective technique to train language models to generate preferred over dispreferred responses. However, this binary "winner-takes-all" approach is suboptimal for vision-language models whose response quality is highly dependent on visual content. In particular, a response may still be faithful to the visual inputs even if it is less preferable than an alternative. The standard Bradley-Terry DPO formulation lacks this nuance, upweighting winning responses without sufficient regard for whether the "losing" response still […]

Ver mais

arXiv:2404.15209v3 Announce Type: replace-cross Abstract: In data-driven decision-making in marketing, healthcare, and education, it is desirable to utilize a large amount of data from existing ventures to navigate high-dimensional feature spaces and address data scarcity in new ventures. We explore knowledge transfer in dynamic decision-making by concentrating on batch stationary environments and formally defining task discrepancies through the lens of Markov decision processes (MDPs). We propose a framework of Transferred Fitted $Q$-Iteration algorithm with general function approximation, enabling […]

Ver mais

arXiv:2601.16397v1 Announce Type: new Abstract: Trustworthy clinical summarization requires not only fluent generation but also transparency about where each statement comes from. We propose a training-free framework for generation-time source attribution that leverages decoder attentions to directly cite supporting text spans or images, overcoming the limitations of post-hoc or retraining-based methods. We introduce two strategies for multimodal attribution: a raw image mode, which directly uses image patch attentions, and a caption-as-span mode, which substitutes images with generated captions […]

Ver mais