Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
Modelo de visão e linguagem · 27 B de parâmetros — 341.2 mil downloads e 159 curtidas no Hugging Face.
This GFN Thursday brings more games, more power and more ways to play on GeForce NOW. The cloud gaming service is expanding with a new GeForce RTX 5080-powered server in Toronto, bringing dedicated high performance in the cloud closer to members across the region. NTE: Neverness to Everness also gets an update in the cloud, […]
O modelo do Shanghai AI Laboratory transforma coordenadas atômicas, topologias e redes cristalinas em um vocabulário único e alcança o estado da arte em 67 de 86 benchmarks — mostrando o raciocínio, não só o resultado.
Datalab’s Lift is a focused document extraction tool with a specific promise: give it a PDF or image plus a JSON Schema, and it returns schema-shaped JSON directly. Instead of converting a document to Markdown first and then asking another model to extract fields, Lift reads rendered page images and attempts to emit the final […] The post Datalab Lift vs the Field: How a 9B Schema-First Extractor Compares with NuExtract3, LlamaExtract, Marker, and Docling appeared first on MarkTechPost .
arXiv:2607.07251v1 Announce Type: new Abstract: One of the expected abilities of vision-language models (VLMs) is spatial reasoning ability based on a given text and image. To evaluate the spatial reasoning abilities of VLMs, we focus on the use of spatial deictic expressions, which are defined as spatial expressions whose referent is determined by their situational context, such as ``this'' and ``that''. To handle spatial deictic expressions, VLMs must jointly reason over language and visual sp...
arXiv:2607.06626v1 Announce Type: new Abstract: Recent Vision-Language Models capture increasingly complex aspects of human cognition. Here we ask whether this alignment extends to reward valuation, which we assess in a mechanistic framework built on clinical tests that were developed to evaluate anhedonia and motivational deficits in major depressive disorder. In the brain, anhedonia is frequently linked to dysregulation in the Nucleus Accumbens (NAc) and the broader dopaminergic reward system....
arXiv:2607.06678v1 Announce Type: new Abstract: How can pretrained Vision-Language-Action (VLA) models retain long-horizon visual histories with high-frequency updates without sacrificing efficiency? Existing approaches rely on external memory management, which restrains either the memory horizon or the reactiveness of pretrained policies. To this end, we present NativeMEM, a VLA policy that features long-term and real-time updated memory. At its core is an efficient memory encoding scheme, Nati...
arXiv:2607.06872v1 Announce Type: new Abstract: The increasing accessibility of artificial intelligence has led to a rapid rise in AI-generated videos, making it more difficult to distinguish between real and manipulated content. Many existing detection methods rely on a single model and often struggle to generalize across different types of deepfakes. In this work, we developed a multimodal deepfake detection system that combines both audio and visual analysis using an ensemble of models. The s...
arXiv:2607.06611v1 Announce Type: new Abstract: Automatically recognizing the sentiment, positive or negative, from speech is a challenging task, requiring both the analysis of vocal inflections and the interpretation of uttered words. Recent solutions rely on audio foundation models to solve the task, but it remains unclear if such models can take all aspects into account. To this end, we propose a multimodal solution that integrates audio and text information via cross-modal transformers, wher...
arXiv:2607.06651v1 Announce Type: new Abstract: Federated learning (FL) over mobile and edge devices increasingly involves multimodal models in which clients differ in both sensing capability and computational capacity. Existing update compression schemes typically apply uniform policies across layers and devices, without accounting for modality-specific differences in spectral structure and compressibility. We propose MESH-FL, an entropy-guided matrix product state (MPS) update-compression fram...
arXiv:2607.06875v1 Announce Type: new Abstract: Understanding and forecasting audience reactions to video content are crucial for improving content creation, recommendation systems, and media analysis. To enable audience reaction prediction and other content engagement applications, we introduce $\textbf{Video2Reaction}$, a multimodal dataset that maps short movie segments to a distribution of $\textit{induced emotions}$ of viewers in the wild, as expressed through social media. $\textbf{Video2R...
arXiv:2607.06943v1 Announce Type: new Abstract: Multimodal learning robust to missing modalities is essential for real-world applications. Existing methods mainly focus on inter-modality missing, where entire modalities are absent, while overlooking intra-modality degradation, where modalities are present but severely corrupted. In practice, these two types of missing often coexist, making existing approaches ineffective. To address this limitation, we propose General Incomplete Multimodal Learn...