Visão Computacional — Radar de IA

Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data

arXiv:2607.02636v1 Announce Type: new Abstract: Object detection is a fundamental capability for AI-driven perception in safety-critical drone and edge-vision systems, including disaster response, operational security environments, infrastructure monitoring and defense applications. Robust model performance in such environments depends on large, continuously updated datasets. However, training high-performing detectors typically requires centralizing aerial imagery, which raises privacy, regulat...

07.07.2026

Blog LLMs & Texto

Demonstrating Generalization Failures via Mixtures of Conditional Policies

arXiv:2607.03478v1 Announce Type: new Abstract: Post-training of frontier language models is conducted on curated task suites, and inevitably leaves a distribution shift between training and deployment environments. This exposes developers to generalization failures, which are relatively poorly understood. To better understand such generalization failures, we believe the community should construct clean demonstrations under simplified conditions. To facilitate this, we propose a simple and flexi...

07.07.2026

Blog LLMs & Texto

The Classics at SemEval-2026 Task 3: Combining Transformer Models and LLM-Generated Annotations for Dimensional Aspect-Based Sentiment Analysis

arXiv:2607.03414v1 Announce Type: new Abstract: This paper presents an approach to the SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis. We investigate methods for moving beyond traditional categorical sentiment (e.g., positive or negative) to predict fine-grained, real-valued scores for sentiment "valence" (positivity) and "arousal" (intensity). We participate in two subtasks: predicting these scores for given aspects (Subtask 1) and extracting full sets of sentiment details, in...

07.07.2026

Blog LLMs & Texto

Echoes of Unrest: A Multimodal NLP Framework for Early Warning of Fake News and Violence-Driven Mob Activity

arXiv:2607.02734v1 Announce Type: new Abstract: Rapid growth in social media has transformed global communication by enabling fast information exchange, but it has also accelerated the spread of misinformation. Fake news, manipulated content, and provocative narratives are increasingly linked to social unrest, political instability, and mob violence. Incidents in South Asia and elsewhere demonstrate how false information disseminated via platforms such as Facebook and WhatsApp can trigger real-w...

07.07.2026

Blog LLMs & Texto

Dual-Adaptive SAM3: Hierarchical Routing over Low-Rank Expert Layers for Parameter-Efficient Medical Image Segmentation

arXiv:2607.02571v1 Announce Type: new Abstract: The Segment Anything Model with Concepts (SAM3) heralds a new paradigm for open-vocabulary segmentation through natural language interaction, offering significant potential for medical image analysis. However, effectively adapting such a powerful vision-language model to the diverse and nuanced domain of medical imaging remains a key challenge. Naive fine-tuning is parameter-inefficient, while standard Mixture-of-Experts (MoE) methods introduce pro...

07.07.2026

Blog Visão Computacional

Derivations of Error-State Kalman Filter Kinematics for Globally Applicable Aided Inertial Navigation Systems

arXiv:2607.03211v1 Announce Type: new Abstract: Global navigation systems require state estimation algorithms that handle Earth's curvature, Earth's rotation, and gravitational variations. These factors can typically be neglected in local navigation algorithms for robots, drones, etc. In classical error-state Kalman Filtering (ESKF) the error state dynamics are trajectory-dependent. Invariant ESKFs utilize Lie Group symmetries to represent the error, which can render error propagation trajectory...

07.07.2026

Blog LLMs & Texto

Reflective Dialogue or Prompt Refinement? Effects of Tutor Scaffolding on Students' Independent LLM Use for Programming

arXiv:2607.03303v1 Announce Type: new Abstract: While Large Language Models (LLMs) can provide personalized support in learning, several studies have raised concerns regarding their use in education. Importantly, learning depends on how students engage with LLMs. This study examined how two types of LLM-based tutors shape students' prompting practices, learning, and subsequent LLM-use: a Socratic-Guidance (SG) tutor, which structures interaction through dialogic questioning, and a Prompt-Refinem...

07.07.2026

Blog Visão Computacional

From Raw Segmentations to Simulation-Ready Cardiac Meshes: An Automated Framework for Anatomical Reconstruction and Virtual Cohort Generation

arXiv:2607.02564v1 Announce Type: new Abstract: Computational models of the human heart are widely used to study electromechanical and fluid-dynamical cardiac function and to support applications such as in silico clinical trials. However, most studies remain limited to single or patient-specific anatomies, restricting the inclusion of population-level variability required for uncertainty quantification. A key challenge is translating medical-image segmentations, which may contain artifacts, mes...

07.07.2026

Blog Visão Computacional

Classroom Behavior Monitoring with YOLO An Empirical Study in Higher Education Settings

arXiv:2607.02580v1 Announce Type: new Abstract: Classroom behavior monitoring plays a vital role in evaluating student engagement and improving teaching effectiveness. Traditional observation methods remain subjective and lack scalability. This study introduces a real-world dataset of classroom videos collected at the Banking Academy of Vietnam (BAV-Classroom dataset), annotated with nine distinctive behavioral categories. State-of-the-art Computer Vision models were evaluated and compared, with...

07.07.2026

Blog Visão Computacional

Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction

arXiv:2607.02829v1 Announce Type: new Abstract: Existing ViT-based weather forecasting models apply uniform computation across all spatial tokens, even though nearby atmospheric grid points often contain similar values and large regions evolve smoothly over time. This makes much of the intermediate per-token computation redundant. Standard token-efficiency methods, such as pruning or merging, reduce cost by removing or fusing tokens. However, weather forecasting is a spatiotemporal dense predict...

07.07.2026

Blog Visão Computacional

CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification

arXiv:2607.02591v1 Announce Type: new Abstract: High resolution medical images contain fine grained, spatially sparse cues that are critical for diagnosis, yet preserving full resolution incurs substantial computational and memory costs. Most deep models process images uniformly, leading to redundant computation or loss of diagnostic detail under downsampling. We propose Chained Perceptual Refinement, CPR, a coarse to fine framework that formulates medical image analysis as a sequential global t...

07.07.2026

Blog Visão Computacional

CV-DCLR: Causal-Visual Dynamic Label Refinement for Robust Zero-Shot Learning

arXiv:2607.02601v1 Announce Type: new Abstract: Zero-Shot Learning (ZSL) facilitates knowledge transfer via shared semantic spaces. However, a critical bottleneck in this paradigm is Semantic Entanglement, where visual representations are inevitably conflated with visually similar semantic concepts, such as distinguishing the intrinsic traits of a Wolf from the shared features of a Husky. Existing global alignment methods often indiscriminately maximize correlations between visual and semantic m...

07.07.2026