arXiv:2512.04165v4 Announce Type: replace-cross Abstract: Two pressing topics in the theory of deep learning are the interpretation of feature learning (FL) mechanisms and the determination of implicit bias of networks in the rich regime. Current theories of rich FL often appear in the form of high-dimensional non-linear equations, which require computationally intensive numerical solutions. Given the many details that go into defining a deep learning problem, this analytical complexity is a significant and often unavoidable challenge. Here, we […]

Ver mais

How Generative and Agentic AI Shift Concern from Technical Debt to Cognitive Debt This piece by Margaret-Anne Storey is the best explanation of the term cognitive debt I’ve seen so far. Cognitive debt, a term gaining traction recently, instead communicates the notion that the debt compounded from going fast lives in the brains of the developers and affects their lived experiences and abilities to “go fast” or to make changes. Even if AI agents produce code that could […]

Ver mais

arXiv:2601.09746v1 Announce Type: new Abstract: This paper introduces a novel Multi-Agent Cooperative Learning (MACL) framework to address cross-modal alignment collapse in vision-language models when handling out-of-distribution (OOD) concepts. Four core agents, including image, text, name, and coordination agents, collaboratively mitigate modality imbalance through structured message passing. The proposed framework enables multi-agent feature space name learning, incorporates a context exchange enhanced few-shot learning algorithm, and adopts an adaptive dynamic balancing mechanism to regulate inter-agent contributions. Experiments on the VISTA-Beyond […]

Ver mais

In cybersecurity applications where replicability is critical, or when building pseudo-random number generators, it is typical to perform a large number of various tests to check if a sequence of bits is random enough for practical purposes. This is also true in scientific research, to assess whether or not the digits of π or other constants mimic randomness well enough, as discussed in my previous article, here. Technically, one could use the Kolmogorov-Smirnov (KS) distance between two joint […]

Ver mais

arXiv:2602.11328v1 Announce Type: new Abstract: As LLMs integrate into our daily lives, understanding their behavior becomes essential. In this work, we focus on behavioral dispositions$-$the underlying tendencies that shape responses in social contexts$-$and introduce a framework to study how closely the dispositions expressed by LLMs align with those of humans. Our approach is grounded in established psychological questionnaires but adapts them for LLMs by transforming human self-report statements into Situational Judgment Tests (SJTs). These SJTs assess behavior by […]

Ver mais

arXiv:2601.10835v1 Announce Type: new Abstract: As robotics become increasingly integrated into construction workflows, their ability to interpret and respond to human behavior will be essential for enabling safe and effective collaboration. Vision-Language Models (VLMs) have emerged as a promising tool for visual understanding tasks and offer the potential to recognize human behaviors without extensive domain-specific training. This capability makes them particularly appealing in the construction domain, where labeled data is scarce and monitoring worker actions and emotional states […]

Ver mais

arXiv:2601.04221v1 Announce Type: new Abstract: This paper presents a new approach to algorithmic composition, called predictive controlled music (PCM), which combines model predictive control (MPC) with music generation. PCM uses dynamic models to predict and optimize the music generation process, where musical notes are computed in a manner similar to an MPC problem by optimizing a performance measure. A feedforward neural network-based assessment function is used to evaluate the generated musical score, which serves as the objective function […]

Ver mais

arXiv:2601.22241v1 Announce Type: new Abstract: Gradient-free black-box optimization (BBO) is widely used in engineering design and provides a flexible framework for topology optimization (TO), enabling the discovery of high-performing structural designs without requiring gradient information from simulations. Yet, its success depends on two key choices: the geometric parameterization defining the search space and the optimizer exploring it. This study investigates this interplay through a compliance minimization problem for a cantilever beam subject to a connectivity constraint. We benchmark […]

Ver mais

arXiv:2603.02351v1 Announce Type: new Abstract: Recent advancements in neural visual geometry, including transformer-based models such as VGGT and Pi3, have achieved impressive accuracy on 3D reconstruction tasks. However, their reliance on full attention makes them fundamentally limited by GPU memory capacity, preventing them from scaling to large, unordered image collections. We introduce MERG3R, a training-free divide-and-conquer framework that enables geometric foundation models to operate far beyond their native memory limits. MERG3R first reorders and partitions unordered images into […]

Ver mais