// radar de ia

Visão Computacional

Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.

todas LLMs & Texto Geração de Imagem Visão Computacional Áudio & Voz Multimodal Dados & Embeddings Robótica & RL
Blog Visão Computacional

Unifying Active Learning and Semi-Supervised Learning for Medical Image Segmentation

arXiv:2607.25014v1 Announce Type: new Abstract: In practical settings, medical image segmentation models are often developed with limited annotated data rather than fully labeled datasets. Training frequently begins in ultra-low labeled regimes where only a small number of volumes are annotated. In such scenarios, practitioners must simultaneously decide which cases to annotate and how to best use the remaining unlabeled data. Although active learning (AL) and semi-supervised learning (SSL) both...

29.07.2026
Blog Robótica & RL

Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning

arXiv:2607.24996v1 Announce Type: new Abstract: Neural networks are hindered by accumulating dormant neurons and loss of expressivity throughout training, particularly in non-stationary data settings, such as continual supervised and reinforcement learning. Recently, neuron resets have been used to maintain gradient flow and restore plasticity. However, full unit reinitialization often sacrifices peak performance and can destabilize training, leading to policy collapse. To preserve plasticity wi...

29.07.2026
Blog Geração de Imagem

Diff-ID: Identity Consistent Facial Image Generation and Morphing via Diffusion Models

arXiv:2607.25078v1 Announce Type: new Abstract: Generative diffusion models have revolutionized facial image synthesis, yet robust identity preservation in high resolution outputs remains a critical challenge. This issue is especially vital for security systems, biometric authentication, and privacy sensitive applications, where any drift in identity integrity can undermine trust and functionality. We introduce Diff-ID, a diffusion based framework that enforces identity consistency while deliver...

29.07.2026
Blog Robótica & RL

Amortising Trajectory Optimisation for Residual MPC via Implicit Contact Differentiation

arXiv:2607.24959v1 Announce Type: new Abstract: Differentiable simulation can accelerate contact-rich trajectory optimisation by exposing local sensitivities of task outcomes to controls. Existing approaches either use finite differences, which are expensive and step-size sensitive; differentiate iterative contact solvers by unrolling automatic differentiation (AD), which stores a growing computation trace; or require intricate, solver-specific KKT sensitivity derivations. We introduce an AD-ass...

29.07.2026
Blog Visão Computacional

ObliCity: A Benchmark and Baseline for Roof-to-Ground Projection Displacement Correction

arXiv:2607.25210v1 Announce Type: new Abstract: Oblique-view urban remote sensing imagery inevitably exhibits geometric projection displacements between building roofs and footprints, leading to significant distortions in spatial structure. Existing approaches either ignore these deformations or handle them implicitly within segmentation-based frameworks, where progress is dominated by general segmentation advances rather than improvements in geometric correction. In this work, we explicitly def...

29.07.2026
Blog Visão Computacional

CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention

arXiv:2607.25291v1 Announce Type: new Abstract: The quadratic cost of self-attention makes long-context inference prohibitively expensive, and proxy-based block-sparse attention has become a practical remedy. Existing methods typically rely on a proxy to predict a binary sparse mask and a kernel to consume this mask and perform sparse attention computation. Such an approach is effective under moderate budgets. However, as the budget tightens, the estimated proxy inevitably drops some salient blo...

29.07.2026
Blog Visão Computacional

Track-Leakage-Free Hold-Out Self-Validation for Photogrammetric Reconstruction: Protocol, Sensitivity, and Limits

arXiv:2607.24852v1 Announce Type: new Abstract: Automated photogrammetric inspection emits metric measurements from a 3D reconstruction whose own correctness is normally unknown without an external survey. Can a reconstruction estimate its own reliability with no ground truth? We formalise a track-leakage-free hold-out protocol: a deterministic subset of images is withheld and each re-localised against only 3D points seen by at least two retained images -- a track-level barrier so a view is neve...

29.07.2026
Blog LLMs & Texto

Enabling Fully Integer-Only Inference for Lightweight Detection Transformers

arXiv:2607.24981v1 Announce Type: new Abstract: Vision Transformer detectors now approach the accuracy of CNNs but remain difficult to deploy on NPUs and microcontrollers because key components, including deformable attention, feature fusion, and nonlinear activation functions, are not natively compatible with integer arithmetic. Existing quantized detectors either retain operators such as Softmax, GELU, and LayerNorm or focus on heavyweight backbones, leaving lightweight detection transformers ...

29.07.2026
Blog Visão Computacional

Motion-Acceleration Calibration and Compensation in IMUs without External Equipment for Attitude Estimation Filters

arXiv:2607.25784v1 Announce Type: new Abstract: Attitude estimation based on inertial sensing requires measurements of local angular velocities and local gravity via gyroscopes and accelerometers. However, during the motion of a mobile system the inertial measurement unit (IMU) will be subject to additional accelerations which skews the measurement of local gravity. This effect gets amplified the further away the IMU is from the base of the system. Many attitude estimation filters, such as "Madg...

29.07.2026
Blog LLMs & Texto

Interpretable Column Annotation with LLM-Symbolized Decision Process Materialization

arXiv:2607.25228v1 Announce Type: new Abstract: Column annotation (CA), including column type annotation (CTA) and column property annotation (CPA), aims to identify the meanings of table columns and the semantic relationships among them. Recent CA methods usually use various neural models to learn column representations and directly map them to label categories, thereby (1) sacrificing model interpretability and adaptivity, and (2) overlooking rich label semantics and ultimately limiting accura...

29.07.2026
← anterior 4 / 30 próxima →
350 itens no radar