arXiv:2604.09688v1 Announce Type: new Abstract: Recent large-scale generative models enable high-quality 3D synthesis. However, the public accessibility of pre-trained weights introduces a critical vulnerability. Adversaries can fine-tune these models to steal specialized knowledge acquired during pre-training, leading to intellectual property infringement. Unlike defenses for 2D images and language models, 3D generators require specialized protection due to their explicit Gaussian representations, which expose fundamental structural parameters directly to gradient-based optimization. We propose GaussLock, the first approach designed to defend […]

Ver mais

arXiv:2601.07752v3 Announce Type: replace-cross Abstract: Estimating the Riesz representer is central to debiased machine learning for causal and structural parameter estimation. We propose generalized Riesz regression, a unified framework for estimating the Riesz representer by fitting a representer model via Bregman divergence minimization. This framework includes various divergences as special cases, such as the squared distance and the Kullback–Leibler (KL) divergence, where the former recovers Riesz regression and the latter recovers tailored loss minimization. Under suitable pairs of […]

Ver mais

arXiv:2602.02584v1 Announce Type: new Abstract: The proliferation of AI-assisted “vibe coding” enables rapid software development but introduces significant security risks, as Large Language Models (LLMs) prioritize functional correctness over security. We present Constitutional Spec-Driven Development, a methodology that embeds non-negotiable security principles into the specification layer, ensuring AI-generated code adheres to security requirements by construction rather than inspection. Our approach introduces a Constitution: a versioned, machine-readable document encoding security constraints derived from Common Weakness Enumeration (CWE)/MITRE Top 25 […]

Ver mais

arXiv:2601.08184v3 Announce Type: replace-cross Abstract: Non-asymptotic central limit theorem (CLT) rates play a central role in modern machine learning and operations research. In this paper, we study CLT rates for multivariate dependent data in Wasserstein-$p$ ($W_p$) distance, for general $pge 1$. We focus on two fundamental dependence structures that commonly arise in practice: locally dependent sequences and geometrically ergodic Markov chains. In both settings, we establish the first optimal $mathcal O(n^{-1/2})$ rate in $W_1$, as well as the […]

Ver mais

arXiv:2602.10254v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) layers activate a subset of model weights, dubbed experts, to improve model performance. MoE is particularly promising for deployment on process-in-memory (PIM) architectures, because PIM can naturally fit experts separately and provide great benefits for energy efficiency. However, PIM chips often suffer from large area overhead, especially in the peripheral circuits. In this paper, we propose an area-efficient in-memory computing architecture for MoE transformers. First, to reduce area, we propose a […]

Ver mais

The fundamental tension in conversational AI has always been a binary choice: respond fast or respond smart. Real-time speech-to-speech (S2S) models — the kind that power natural-feeling voice assistants — start talking almost instantly, but their answers tend to be shallow. Cascaded systems that route speech through a large language model (LLM) are far more knowledgeable, but the pipeline delay is long enough to make conversation feel stilted and robotic. Researchers at Sakana AI, the Tokyo-based AI lab […]

Ver mais

arXiv:2408.12739v2 Announce Type: replace-cross Abstract: Quantum Convolutional Neural Networks (QCNNs) are widely regarded as a promising model for Quantum Machine Learning (QML). In this work we tie their heuristic success to two facts. First, that when randomly initialized, they can only operate on the information encoded in low-bodyness measurements of their input states. And second, that they are commonly benchmarked on “locally-easy” datasets whose states are precisely classifiable by the information encoded in these low-bodyness observables subspace. We […]

Ver mais

arXiv:2602.24165v1 Announce Type: cross Abstract: Hypothesis testing in singular statistical models is often regarded as inherently problematic due to non-identifiability and degeneracy of the Fisher information. We show that the fundamental obstruction to testing in such models is not singularity itself, but the formulation of hypotheses on non-identifiable parameter quantities. Testing is inherently a problem in distribution space: if two hypotheses induce overlapping subsets of the model class, then no uniformly consistent test exists. We formalize this overlap […]

Ver mais

arXiv:2512.03851v2 Announce Type: replace Abstract: Neural networks have become a widely adopted tool for modeling nonlinear dynamical systems from data. However, the choice of training strategy remains a key design decision, particularly for simulation tasks. This paper compares two predominant strategies: parallel and series-parallel training. The conducted empirical analysis spans five neural network architectures and two examples: a pneumatic valve test bench and an industrial robot benchmark. The study reveals that, even though series-parallel training dominates current practice, […]

Ver mais