// radar de ia

O que está acontecendo agora

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 Robótica & RL

Cogent AI Team Releases VR-1: A Frontier Cyber Reasoning Model That Composes and Verifies Enterprise Attack Paths

Cogent AI team released Cogent VR-1, a reasoning model post-trained specifically for cybersecurity rather than picking up cyber capability as a side effect of general coding strength. It ships with two companions: IntrusionBench, a benchmark that scores agents on completed enterprise intrusions, and the Cogent AI Harness, a governed runtime for security agents. The launch […] The post Cogent AI Team Releases VR-1: A Frontier Cyber Reasoning Model That Composes and Verifies Enterprise Attack Pa...

03.08.2026
Blog LLMs & Texto

Benchmarks Are Not Monolithic: Sample-Level Auditing and Orchestration for LLM Evaluation

arXiv:2607.28801v1 Announce Type: new Abstract: Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial variation in the demands of individual samples. We introduce a dataset-centric meta-evaluation framework that audits benchmark datasets at the sample level along five latent dimensions: 1. Cognitive and Knowledge Demands, 2. Language and Content Quality, 3. Task Properties, 4. Context, and 5. Ethics,...

03.08.2026
Blog LLMs & Texto

Imbalanced Data Clustering via Targeted Data Augmentation Using GMM and LLM

arXiv:2607.28635v1 Announce Type: new Abstract: In Natural Language Processing (NLP), dealing with underrepresented topics is challenging, especially in unsupervised tasks where clustering might not adequately capture minority topics. To tackle this challenge, our paper presents a novel unsupervised data augmentation method that integrates Gaussian Mixture Models (GMMs) and Large Language Models (LLMs). Due to their flexibility and robustness, GMMs can detect clusters corresponding to underrepre...

03.08.2026
Blog Multimodal

AquaJEPA: Action-Conditioned Multimodal Predictive Representations for Underwater Robot Dynamics

arXiv:2607.29393v1 Announce Type: new Abstract: Underwater robots combine complementary sensors whose reliability changes abruptly with water visibility, viewpoint, and vehicle motion. We introduce AquaJEPA, an action-conditioned joint-embedding predictive model that fuses an RGB camera, forward-looking sonar, and proprioception with explicit sensor validity. It predicts a future latent target conditioned on eight-thruster commands and supplies velocity and sonar-profile predictions to a shared ...

03.08.2026
Blog Robótica & RL

Uncertainty-Aware Deepfake Detection via Multi-View Structural Learning

arXiv:2607.28769v1 Announce Type: new Abstract: Security-critical biometric and forensic applications require accurate predictions and reliable confidence estimates, particularly under distribution shift. This challenge is especially acute for deepfake detection, where foundation-model-based detectors often exhibit overconfident predictions on out-of-distribution manipulations, which limits their suitability for operational deployment. We propose an uncertainty-aware deepfake detection framework...

03.08.2026
Blog Robótica & RL

Best Friends, Not Forever: Evaluating Long-Horizon Persona Collapse and Behavioral Drift in AI Companions

arXiv:2607.28818v1 Announce Type: new Abstract: As AI companions increasingly mediate repeated social interaction, users may rely on a stable role and shared history, yet locally acceptable replies do not ensure that either persists. We study two observable long-horizon failures: 'persona collapse', the loss of a deployed role, boundaries, values, or style, and 'behavioral drift', the gradual or recurrent erosion of those properties. We introduce ANCHOR, a controlled synthetic audit that separat...

03.08.2026
Blog LLMs & Texto

Rethinking Detection Calibration: A Coordinate and Direction Perspective

arXiv:2607.29040v1 Announce Type: new Abstract: Deep learning based object detectors require trustworthiness beyond competitive detection performance, but deep neural networks are prone to overconfident predictions, assigning high confidence scores to predictions that are likely to be inaccurate. To improve the alignment between confidence scores and prediction accuracy, existing methods calibrate confidence scores based on box-level localization, such as precision or intersection over union wit...

03.08.2026
Blog LLMs & Texto

The Asymmetric Effects of Knowledge Distillation on Bias in Small Language Models

arXiv:2607.28639v1 Announce Type: new Abstract: We show that knowledge distillation in small instruction-tuned language models has asymmetric effects on bias. On unambiguous tasks (BBQ-disambig), response-based distillation from a Gemma-2-9B teacher improves context-following: for the most biased baseline (SmolLM2-1.7B-Instruct), it cuts the context-overriding error rate from 44% to 24%. On ambiguous tasks (BBQ-ambig), the same distillation destroys per-item refusal calibration: 15% of items whe...

03.08.2026
Blog LLMs & Texto

Can Zero-Shot LLMs Predict Child Malnutrition? A Fairness and Temporal Robustness Study

arXiv:2607.29082v1 Announce Type: new Abstract: Child malnutrition remains a major public health challenge in low- and middle-income countries, particularly in South Asia, where early identification of vulnerable children is critical for timely intervention and resource allocation. This study aims to evaluate the feasibility, fairness, and temporal robustness of using a pretrained large language model (LLM) in a zero-shot setting for child stunting prediction using population health survey data....

03.08.2026
Blog LLMs & Texto

TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text

arXiv:2607.28862v1 Announce Type: new Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage. Unlearnable examples (UEs) offer a promising defense by introducing carefully designed perturbations into data such that models trained on them exhibit degraded utility. However, existing methods for text protection are pri...

03.08.2026
Blog LLMs & Texto

Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models

arXiv:2607.28707v1 Announce Type: new Abstract: Entropy-based pruning has been proposed as an effective method for compressing Chain-of-Thought (CoT) reasoning with negligible accuracy loss. We test the robustness of low- and high-entropy CoT step selection methods across various models and reasoning tasks, showing that entropy offers no advantage over random pruning in any evaluated setting. Moving from sentences to tokens, we then show that retaining low-entropy tokens seems effective only on ...

03.08.2026
← anterior 3 / 418 próxima →
5015 itens no radar