// radar de ia

Multimodal

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 Multimodal

MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models

arXiv:2606.24155v1 Announce Type: new Abstract: Existing medical AI benchmarks lack process visibility, atomic skill evaluation, and integrated hallucination detection. We introduce MedBench v5, a redesigned benchmark for clinical multimodal models (language, vision-language, and agent systems) that moves from static QA to dynamic, process-oriented evaluation. MedBench v5 features: (1) a dual-dimensional framework combining Clinical Cognitive Responsiveness (14 sub-dimensions) and Medical Atomic...

24.06.2026
Blog LLMs & Texto

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

arXiv:2606.23885v1 Announce Type: new Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder. However, existing methods typically align a fixed layer of the language backbone, overlooking the fine-grained structure of Transformer models. In this work, we propose Head-Wise Representation Alignment (HeRA), a method that enforces cross-modal ...

24.06.2026
Blog Multimodal

An LMM for Precisely Grounding Elements in Documents

arXiv:2606.24118v1 Announce Type: new Abstract: Visual grounding in documents is a crucial ability for Large Multimodal Models (LMMs) in areas such as document understanding, deep research and document error detection. However, existing approaches exhibit poor grounding precision in text-rich document images, often failing to accurately locate the critical document elements needed for reliable reasoning. To address this gap, we introduce PreciseDoc, an LMM specifically designed for precise eleme...

24.06.2026
Blog Robótica & RL

Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos

arXiv:2606.24448v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models require large-scale video-action pairs, yet real teleoperation remains scarce. While generated robot videos offer a scalable alternative, existing methods treat them as real robot data by recovering pseudo-actions from synthesized pixels. We argue that deriving low-level control from generated visuals is a mismatched abstraction. A video captures only \emph{geometry}: the spatial trajectory representing the \emph...

24.06.2026
Blog Multimodal

Listening makes Vision Clear for VLMs

arXiv:2606.23763v1 Announce Type: new Abstract: Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens. However, we observe that highest attention regions are not always consistent with the intended semantic token. This probably stems from decoding drift, where language priors from previously generated answer tokens accumulate and mismatch with visual attention. Besides the priors from previous answer tokens, we find that structural tokens...

24.06.2026
Blog Multimodal

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

arXiv:2606.24388v1 Announce Type: new Abstract: We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs). The dataset is designed to be diverse, representative, and practical, extending existing benchmarks by covering 10 high-level categories and 55 subcategories of harmful intents. Our primary goal is to make adversarial data accessible to the research community, given the computational cost and complexity of generating large numbers...

24.06.2026
Blog LLMs & Texto

Navigating User Behavior toward Personalized Multimodal Generation

arXiv:2606.24196v1 Announce Type: new Abstract: Modern AIGC pipelines deliver high-fidelity images and videos but presuppose a well-formed creation instruction, while end users rarely articulate visual details, leaving generators misaligned with user demand. We study personalized content generation, which turns a user's interaction history into an executable instruction for downstream synthesis, and identify two obstacles: behavior must be encoded in a form legible to language reasoning, and the...

24.06.2026
Blog Robótica & RL

G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models

arXiv:2606.24472v1 Announce Type: new Abstract: Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-language backbones, but their visual tokens remain grounded in 2D image coordinates rather than the calibrated geometry of the robot's cameras -- a mismatch especially pronounced in multi-camera setups, where views are coupled by known intrinsics and extrinsics yet processed as independent images. We ...

24.06.2026
Blog Multimodal

Trustworthy Image Authentication using Forensic Knowledge Graphs

arXiv:2606.23917v1 Announce Type: new Abstract: Advances in generative AI have made image falsification highly realistic, demanding trustworthy authentication systems. Existing forensic detectors can target certain forgery types but lack interpretability, while vision-language models (VLMs) provide explanations but cannot exploit forensic traces for reliable detection. We propose Forensic Knowledge Graphs (FKGs), a unified framework that integrates forensic evidence extraction, structured reason...

24.06.2026
← anterior 32 / 39 próxima →
467 itens no radar