10 resultados para "diffusion"
Geração de Imagem: O Guia dos Modelos de Difusão
Geração de ImagemEntenda a geração de imagem por IA: da era das GANs aos modelos de difusão como Stable Diffusion e FLUX, como funcionam, prompts, ControlNet, usos e dilemas éticos.
Como Funciona a Difusão (Sem Matemática)
Geração de ImagemA difusão explicada sem fórmulas: partir do ruído e limpá-lo passo a passo, como o modelo é treinado e o papel do texto e da latent diffusion.
FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents
Geração de ImagemarXiv:2607.28945v1 Announce Type: new Abstract: Synthetic tabular data is increasingly used in privacy-preserving data sharing, data augmentation, and to mitigate downstream classifier bias. State-of-the-art tabular diffusion models such as TabDDPM and TabSyn achieve excellent distributional fidelity but offer no mechanism for fairness; conversely, fairness-aware tabular generators (DECAF, FairTGAN, FairTabDDPM) impose explicit fairness penalties at training time, yielding modest fairness gains ...
Faster but Different: Diagnosing and Controlling Content Drift in Accelerated Multimodal Diffusion Language Models
LLMs & TextoarXiv:2607.29079v1 Announce Type: new Abstract: Training-free acceleration makes diffusion-based multimodal large language models (dMLLMs) more deployable, but it may silently change generated content. We study this serving-time consistency problem on 300 real images, comparing Fast-dLLM outputs with the same model's unaccelerated outputs. Across the mild parallelism induced in our long-form setting (1.05--1.25 committed tokens per step), confidence-threshold tuning changes decoding behavior but...
DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models
Geração de ImagemarXiv:2607.28936v1 Announce Type: new Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space. However, the decision boundaries of deep face recognition (FR) systems are often sufficiently narrow that they can be conflated, rendering the models vulnerable to adversarial attacks. In such scenarios, the FR system fails to distinguish between an authentic source and a meticulously crafted adversarial face. Existing adversa...
Temporal Policy: History-Initialized Action Generation for Robotic Learning from Demonstration
Robótica & RLarXiv:2607.29482v1 Announce Type: new Abstract: By relying on independent couplings from uninformative Gaussian priors, standard diffusion and flow matching models are forced to learn complex, high-cost vector fields to reach the physical action space. Generative models excel at capturing multimodal behaviors for robotic Learning from Demonstration (LfD), but often suffer from high inference cost. This paper introduces Temporal Policy, a generative framework based on stochastic interpolants that...
SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
Geração de ImagemarXiv:2607.27431v1 Announce Type: new Abstract: Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties. Existing diffusion and flow-matching models produce high-quality backbones on SE(3)^N, but inference requires numerically integrating an ODE over hundreds of network evaluations, each involving a Lie group exponential map - a bottleneck for high-throughput design campaigns. We introduce SE(3)-MeanFlow, a few-step ge...
Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models
LLMs & TextoarXiv:2607.27512v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in multi-agent environments. However, the processes by which beliefs form and propagate among interacting LLMs remain poorly understood. We introduce CoevolveSim, a framework for studying belief diffusion within networked LLM populations. CoevolveSim allows us to isolate and study three factors: domain specialization, social-role assignment, and social network structure. Within this framework, ...
4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans
LLMs & TextoarXiv:2607.27634v1 Announce Type: new Abstract: Generating high-quality 360-degree dynamic human assets from text prompts is challenging. Existing methods usually synthesize monocular or multi-view videos first and then fit a 4D representation, which is expensive and often causes incomplete geometry or view-inconsistent renderings. We present 4DHumanDiff, a diffusion framework that directly generates dynamic humans represented by 4D Gaussian Splatting (4DGS) from text prompts. By modeling the st...
ZUNA1.1: A more flexible EEG foundation model for Denoising and Super-resolution
Geração de ImagemarXiv:2607.27308v1 Announce Type: new Abstract: We introduce ZUNA1.1, a 380M-parameter diffusion autoencoder for flexible EEG signal reconstruction. ZUNA1.1 is capable of reconstructing variable length sequences of up to 30s, with an arbitrary number of EEG channels at arbitrary scalp locations, and can reconstruct arbitrary temporal intervals within channels in addition to reconstructing entire channels. We demonstrate that ZUNA1.1 performs at least on par with our earlier ZUNA1 model, while be...