// radar de ia

Geração de Imagem

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 Geração de Imagem

MorphUNet: Alpha-Controlled Biometric Transport for Diffusion-Based Face Morphing Attacks

arXiv:2607.25092v1 Announce Type: new Abstract: Face morphing attacks create synthetic images verifiable against multiple identities, threatening border control and identity verification systems. We introduce MorphUNet, a diffusion morphing framework formulating two-parent generation as alpha-controlled biometric transport: each parent is decomposed into CLIP appearance and ArcFace identity evidence, aligned into a CLIP-compatible token space, with the two contributors preserved as separate iden...

29.07.2026
Blog Dados & Embeddings

Beyond Background Bias: Saliency-Driven Prototype Alignment for Dataset Distillation

arXiv:2607.25318v1 Announce Type: new Abstract: Dataset distillation aims to synthesize compact datasets that can approximate the performance of full-data training while significantly reducing computational and storage costs. However, diffusion-based distillation methods often struggle to preserve structural coherence and generalization, especially in visually complex domains. This issue often stems from latent prototypes that are weakly aligned with class-discriminative regions and contaminated...

29.07.2026
Blog Geração de Imagem

OrganLens: Organ-Specific Representation Learning for CT Foundation Models

arXiv:2607.25164v1 Announce Type: new Abstract: A CT examination captures multiple organs, but many biomedical questions concern abnormalities, prognosis, or longitudinal change in a specific organ. These questions require a separate representation for each organ within the same CT volume. Existing CT foundation models commonly produce a single volume-level representation, while recent anatomy-aware methods either encode pre-separated organ volumes or explicitly disentangle images into organ tok...

29.07.2026
Blog Geração de Imagem

ScaleResfusion: Residual Rectified Flow based on Residual Vector Field

arXiv:2607.25275v1 Announce Type: new Abstract: Real-world Image Restoration (Real-IR) aims to recover high-quality (HQ) images from complex and unknown degradations. Although recent diffusion-based methods have substantially improved perceptual quality, their current designs leave two key challenges unresolved. Methods that start from Gaussian noise are slow and often less faithful to the degraded input. Residual-based methods usually train from scratch, which makes it hard to exploit modern pr...

29.07.2026
Blog LLMs & Texto

Accurate structural modeling of chemically diverse molecular interfaces with Vilya-2

arXiv:2607.25156v1 Announce Type: new Abstract: Structure-prediction networks built on co-evolutionary statistics have transformed protein-based drug discovery, yet their accuracy does not extend to peptide therapeutics--an increasingly important modality defined by non-canonical residues, macrocyclization, and complex topologies. We introduce Vilya-2, a diffusion transformer that extends the all-atom representation of Vilya-1 from modeling individual molecules to modeling their interactions wit...

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 Geração de Imagem

HeAD-CP: Heterophily-Aware Diffused Conformal Prediction Sets for Graph Neural Networks

arXiv:2607.25273v1 Announce Type: new Abstract: Conformal prediction (CP) provides distribution-free uncertainty quantification, and its extension to graphs is an active research direction. Diffused Adaptive Prediction Sets (DAPS) is a widely used graph-aware diffusion baseline, propagating Adaptive Prediction Sets (APS) non-conformity scores along edges with a uniform coefficient $\lambda$. We identify a fundamental shortcoming of this design: the uniform low-pass diffusion presupposes graph ho...

29.07.2026
Blog Robótica & RL

Lantern: Conflict-Aware Gradient Blending for Physics-Guided Diffusion Models in Calorimeter Simulation

arXiv:2607.25060v1 Announce Type: new Abstract: Monte Carlo simulation of calorimeter showers is a principal bottleneck for the High-Luminosity LHC, and diffusion models have emerged as fast, high-fidelity surrogates. Their denoising objective is purely statistical, however: a model can minimize it while placing the physics wrong. Existing physics-informed generative methods cannot close this gap, because they assume a closed-form law, a governing PDE residual or a hard per-sample constraint, th...

29.07.2026
Blog LLMs & Texto

CaRE: Protocolo de Avaliação de Remascaramento Ciente de Computação para Modelos de Linguagem por Difusão Mascarada

arXiv:2607.24763v1 Tipo de Anúncio: novo Resumo: Os modelos de linguagem por difusão mascarada (MDLMs) estão avançando rapidamente, mas os padrões de avaliação necessários para interpretar de forma confiável seu progresso não acompanharam esse ritmo. Apesar de os MDLMs estarem se tornando competitivos com os modelos de linguagem autorregressivos, sete artigos recentes sobre remascaramento avaliam sob configurações incompatíveis, variando contagens nominais de passos, métricas e temperaturas de amostragem sem controlar conjuntamente esses fatores, o que torna seus rankings de estratégias amplamente incomp...

29.07.2026
Blog LLMs & Texto

Neuromorphic Diffusion Language Models: Addressing Compute and Memory Bottlenecks via Sparsity and Block Denoising

arXiv:2607.24841v1 Announce Type: new Abstract: Autoregressive (AR) large language models (LLMs) are inherently inefficient at inference time because each generated token requires accessing the full set of model parameters, leading to low operational intensity and high energy consumption. Masked diffusion language models (MDLMs) partially address this limitation for memory-bound settings by allowing multiple tokens to be generated per parameter access. In order to further enhance inference effic...

29.07.2026
Blog Geração de Imagem

Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed

arXiv:2607.24898v1 Announce Type: new Abstract: State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users. Our empirical evidence shows that these detectors fail to shield marginalized communities: approximately 35% of generated images labeled safe are considered harmful by disability communities. In this position paper, we argue for community-specific toxicity detection (CTD). To de...

29.07.2026
← anterior 5 / 35 próxima →
420 itens no radar