Visão Computacional — Radar de IA

qZACH-ViT: Quantization-Aware Intrinsic Explanations with Recursive Attribution-Stabilized Optimization

arXiv:2607.15421v1 Announce Type: new Abstract: Compact medical-image classifiers need efficiency and interpretable evidence, yet these goals are often addressed separately. We introduce qZACH-ViT, a quantization-aware extension of the zero-token (CLS-token-free), position-free ZACH-ViT backbone with recursive intrinsic patch-level class evidence. We also introduce Recursive Attribution-Stabilized Optimization (RASO), which norm-matches classification and attribution gradients and removes attrib...

20.07.2026

Blog LLMs & Texto

Are All Tokens Necessary for Visual Place Recognition? An Empirical Study of Token Reduction for Efficient Inference

arXiv:2607.15563v1 Announce Type: new Abstract: Recent visual place recognition (VPR) methods based on vision transformers, particularly foundation models, have achieved remarkable recognition performance. However, these models process all visual tokens throughout the entire network, resulting in substantial computational overhead, which hinders their deployment in real-time and resource-constrained scenarios. A natural question thus arises: are all visual tokens necessary for VPR? To answer thi...

20.07.2026

Blog Visão Computacional

Training-Free Open-Vocabulary 3D Point-Cloud Segmentation on the Generalized Few-Shot Benchmark

arXiv:2607.15331v1 Announce Type: new Abstract: Generalized few-shot 3D point-cloud segmentation (GFS-PCS) asks a model to segment a scene into many base classes seen at training time and a set of novel classes. The state of the art reaches novel classes by reconciling a dense but noisy 3D vision-language prior with the few-shot support, but it pays for this with base 3D labels, per-episode training, and the support annotations themselves. We ask how far the same reconciliation can go with none ...

20.07.2026

Blog LLMs & Texto

Kolmogorov--Arnold Networks for Small Language Models

arXiv:2607.15525v1 Announce Type: new Abstract: Kolmogorov--Arnold Networks (KANs) replace fixed node activations with learned one-dimensional edge functions, offering an explicit interface for interpretation and a possible alternative to transformer feed-forward networks. We test these claims separately. In a six-layer, 10M-parameter B-spline KAN, we reconstruct all 884,736 feed-forward edges: 87.8\% exceed (NLS>0.1) and 0.4\% are inactive. Pruning the lowest-activity 20--25\% causes negligible...

20.07.2026

Blog LLMs & Texto

A Generative Partially Specified Finite State Machine Approach to Complex Behaviour Planning

arXiv:2607.15674v1 Announce Type: new Abstract: Autonomous robots operating in dynamic environments require behaviour planning systems that combine reactivity, interpretability, and adaptability. While Large Language Models have been successfully integrated with Behaviour Trees for dynamic replanning, Finite State Machines, despite their widespread adoption and computational efficiency, remain unexplored for generative approaches. We propose a Generative Partially Specified Finite State Machine ...

20.07.2026

Blog LLMs & Texto

Large Language Models as Unified Multimodal Learners for Clinical Prediction

arXiv:2607.15380v1 Announce Type: new Abstract: Electronic health records combine free-text clinical narratives with structured measurements such as vital signs, laboratory values, and comorbidities. Yet most clinical prediction systems still rely on task-specific fusion architectures, pairing dedicated encoders for each modality with learned combination mechanisms that must be re-engineered for every new task and clinical setting. We propose a simpler alternative: convert all patient data, rega...

20.07.2026

Blog LLMs & Texto

LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4

arXiv:2607.15509v1 Announce Type: new Abstract: We present a fully automated closed-loop AutoML framework that uses GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers for cross-lingual handwritten optical character recognition. Each large language model independently generates, trains, evaluates, and iteratively refines neural network architectures using performance feedback from previous trials. The framework is evaluated on Arabic, Persian, and English handwriting d...

20.07.2026

Blog LLMs & Texto

BCG-Former: Toward Pareto-Efficient Hyperspectral Image Classification via Band-Contextual Gating

arXiv:2607.15639v1 Announce Type: new Abstract: Hyperspectral image (HSI) classification systems are increasingly deployed on platforms with strict computational budgets, such as UAVs and small spaceborne sensors. In these settings, accuracy alone is not enough; the model must also run within tight latency and memory constraints. Most recent HSI classifiers, however, focus on accuracy and pay relatively little attention to these constraints. We propose BCG-Former, a lightweight CNN-Transformer h...

20.07.2026

Blog Robótica & RL

Implicit Virtual Leader: Decentralized Vision-Only Relative Pose Estimation for Multi-Robot Formations

arXiv:2607.15708v1 Announce Type: new Abstract: Classical leader-follower formation control suffers from single points of failure and error propagation, and relies on absolute localization sensors that are ill-suited for GPS-denied environments. We address these limitations by introducing a fully decentralized, vision-only relative pose estimation framework based on Graph Neural Networks (GNNs). The key idea is the implicit virtual leader (IVL): a non-physical formation reference frame that is n...

20.07.2026

Blog Geração de Imagem

Diffusion models recover accurate mixture weights despite score function insensitivity

arXiv:2607.15485v1 Announce Type: new Abstract: Score-based generative models exhibit a puzzling behavior: they often appear to cover all modes of a target multimodal distribution and yet may fail to learn the correct relative mode amplitudes, which can be interpreted as mixture weights. We resolve this apparent paradox by relating the diffusion score matching (DSM) loss to the error in estimating mixture weights from generated samples. We show that, even when the target score is insensitive to ...

20.07.2026

Blog Visão Computacional

Benchmarking MRI Representations for Deep Learning-Based Focal Cortical Dysplasia Segmentation

arXiv:2607.15605v1 Announce Type: new Abstract: Focal cortical dysplasia (FCD) is one of the leading structural causes of drug-resistant focal epilepsy, yet its subtle and heterogeneous imaging characteristics make accurate identification and delineation challenging on conventional magnetic resonance imaging (MRI). Although T1-weighted (T1w) and fluid-attenuated inversion recovery (FLAIR) images are routinely acquired for presurgical evaluation, the contribution of different MRI representations ...

20.07.2026

Blog Visão Computacional

An Empirical Study of Handcrafted Feature Learning and Convolutional Neural Networks for Facial Expression Recognition

arXiv:2607.15288v1 Announce Type: new Abstract: Facial expression recognition is an important computer vision task with applications in human--computer interaction, mental health monitoring, driver alert systems, and behavioral analysis. While convolutional neural networks (CNNs) dominate modern facial expression recognition, handcrafted feature descriptors such as Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) remain useful classical baselines. This study compares HOG wit...

20.07.2026