digitado

arXiv:2604.09849v1 Announce Type: new Abstract: We study whether in-domain pretraining of Bidirectional Encoder Representations from Transformer (BERT) model improves subdomain-level detection of exfiltration at low false positive rates. While previous work mostly examines fine-tuned generic Transformers, it does not aim to isolate the effect of pretraining on the downstream task of classification. To address this gap, we develop a controlled pipeline where we freeze operating points on validation and transfer them to the test set, thus enabling clean […]

Ver mais

arXiv:2604.09841v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly adapted through domain-specific fine-tuning, yet it remains unclear whether this improves reasoning beyond superficial visual cues, particularly in high-stakes domains like medicine. We evaluate four paired open-source VLMs (LLaVA vs. LLaVA-Med; Gemma vs. MedGemma) across four medical imaging tasks of increasing difficulty: brain tumor, pneumonia, skin cancer, and histopathology classification. We find that performance degrades toward near-random levels as task difficulty increases, indicating limited clinical reasoning. Medical fine-tuning […]

Ver mais

arXiv:2604.09839v1 Announce Type: new Abstract: Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in output behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating activations into human-readable explanations and safety research (e.g., studying jailbreakability). However, it is unclear whether steered activation states are realizable by any textual prompt. In this work, we cast this question as a surjectivity problem: for a fixed model, […]

Ver mais

arXiv:2604.09838v1 Announce Type: new Abstract: We present a novel diffusion-based framework for synthesizing 2D vector fields from sparse, coherent inputs (i.e., streamlines) while maintaining physical plausibility. Our method employs a conditional denoising diffusion probabilistic model with classifier-free guidance, enabling progressive reconstruction that preserves both geometric and physical constraints. Experimental results demonstrate our method’s ability to synthesize plausible vector fields that adhere to physical laws while maintaining fidelity to sparse input observations, outperforming traditional optimization-based approaches in terms of […]

Ver mais

arXiv:2604.09836v1 Announce Type: new Abstract: AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this stage have become saturated and only measure performance on constrained outputs. To help address this gap, we introduce COMPOSITE-STEM, a benchmark of 70 expert-written tasks in physics, biology, chemistry, and mathematics, curated by doctoral-level researchers. Our benchmark combines exact-match grading […]

Ver mais

arXiv:2604.09835v1 Announce Type: new Abstract: Existing full-body Gaussian avatar methods primarily optimize global reconstruction quality and often fail to preserve fine-grained facial geometry and expression details. This challenge arises from limited facial representational capacity that causes difficulties in modeling high-frequency pose-dependent deformations. To address this, we propose F3G-Avatar, a full-body, face-aware avatar synthesis method that reconstructs animatable human representations from multi-view RGB video and regressed pose/shape parameters. Starting from a clothed Momentum Human Rig (MHR) template, front/back positional […]

Ver mais

arXiv:2604.09833v1 Announce Type: new Abstract: Physical implementations of neural computation now extend far beyond silicon hardware, encompassing substrates such as memristive devices, photonic circuits, mechanical metamaterials, microfluidic networks, chemical reaction systems, and living neural tissue. By exploiting intrinsic physical processes such as charge transport, wave interference, elastic deformation, mass transport, and biochemical regulation, these substrates can realize neural inference and adaptation directly in matter. As silicon GPU-centered AI faces growing energy and data-movement constraints, physical neural computation is […]

Ver mais

arXiv:2604.09829v1 Announce Type: new Abstract: Gaze-following in child-robot interaction improves attention, recall, and learning, but requires expensive platforms ($30,000+), sensors, algorithms, and raises privacy concerns. We propose a framework that avoids sensors and computation entirely, instead relying on the human visual system’s assumption of convexity to produce perceptual gaze-following between a robot and its viewer. Specifically, we motivate sub-dollar cardboard robot design that directly implements the brain’s own gaze computation pipeline in reverse, making the viewer’s perceptual system […]

Ver mais

arXiv:2604.09827v1 Announce Type: new Abstract: This paper empirically examines the practical validity of the official evaluation criteria underpinning the Research Productivity (PQ) Grant framework, as governed by the Brazilian National Council for Scientific and Technological Development (CNPq). By operationalizing regulatory dimensions (including bibliographic output, human resource training, and scientific recognition) as measurable variables extracted from CVs and OpenAlex bibliometric data, we treat policy-defined indicators as testable hypotheses rather than a priori assumptions. Using a block-based adaptation of the […]

Ver mais

arXiv:2604.09824v1 Announce Type: new Abstract: Vision language action (VLA) models enable generalist robotic agents but often exhibit language ignorance, relying on visual shortcuts and remaining insensitive to instruction changes. We present Prospective Grounding and Alignment VLA (ProGAL-VLA), which constructs a 3D entity-centric graph (GSM), uses a slow planner to produce symbolic sub-goals, and aligns them with grounded entities via a Grounding Alignment Contrastive (GAC) loss. All actions are conditioned on a verified goal embedding $g_t$, whose attention entropy […]

Ver mais