Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
Modelo de visão e linguagem · 32 B de parâmetros — 0 downloads e 73 curtidas no Hugging Face.
A MiniMax lançou um modelo que lê texto, imagem, vídeo e áudio como um único contexto e devolve clipes de até 15 segundos em 2K com som estéreo nativo. O diferencial não é a resolução — é tratar edição, geração e transferência de estilo como a mesma operação, e cobrar por isso menos de um terço do preço convencional.
Modelo de multimodal · 8 B de parâmetros — 121 downloads e 53 curtidas no Hugging Face.
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 ...
arXiv:2607.29169v1 Announce Type: new Abstract: Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visual observations, robot states, and executed actions. We introduce ActFovea, a plug-and-play safeguarding framework that detects and mitigates such failures without retraining or modifying the underlying VLA policy. ActFovea uses robot kinematics, proprioceptive states, and...
arXiv:2607.28986v1 Announce Type: new Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers. Existing retrieval-augmented methods score image-text alignment once, at retrieval, then commit the captioner's autoregressive beam under language-model probability alone, leaving the decoder without further visual grounding feedback. Progress has stalled, with n...
arXiv:2607.28637v1 Announce Type: new Abstract: This paper presents our system for the CHiPSAL 2026 shared task on multimodal hate speech and sentiment detection in Nepali memes. We address both subtasks: binary hate speech classification and three-class sentiment analysis. Our approach adapts the Robust Adaptation of Hateful Meme Detection (RA-HMD) framework using Qwen3-VL-8B-Instruct, a state-of-the-art vision-language model with native Devanagari support. We employ a two-stage training pipeli...
arXiv:2607.29002v1 Announce Type: new Abstract: Online shoppers increasingly turn to AI shopping assistants, using images and multi-turn dialogue to express and refine product needs that are difficult to articulate in text alone. However, existing benchmarks largely rely on text-only or synthetic requests, underrepresenting complex real-world shopping requirements jointly expressed through images and language. We introduce MMShopBench, the first real-log benchmark for multimodal, multi-turn shop...
arXiv:2607.28969v1 Announce Type: new Abstract: Although Large Language Models (LLMs) have demonstrated promising safety performance, extending them to Multimodal Large Language Models (MLLMs) exposes a significant gap between expanded multimodal capabilities and existing safety mechanisms. Current defenses remain predominantly confined to specific modal settings, thereby limiting their robustness against broader cross-modal threats. To bridge this gap, we introduce SafeNexus, a cross-modal safe...
arXiv:2607.28640v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) should generate consistent responses given semantically equivalent inputs across modalities. However, we observe a systematic discrepancy in model predictions under such cross-modal variations. Specifically, we define the modality gap as the difference in model performance under semantically equivalent textual and multimodal inputs. We introduce TokenSwap, a method that constructs such inputs by replacing te...
arXiv:2607.29052v1 Announce Type: new Abstract: End-to-end (E2E) autonomous driving aims to learn a direct mapping from visual observations to control actions. However, these E2E models often act as black boxes and struggle with complex scenarios. To address this, recent works incorporate Vision-Language Models (VLMs) to provide explicit reasoning, enhancing both interpretability and driving robustness. These approaches typically rely on pre-generated annotations, which suffer from potentially f...
arXiv:2607.29039v1 Announce Type: new Abstract: Multimodal medical anomaly detection identifies samples deviating from normal patterns, where scarce abnormal cases make normality modeling from normal data practical. In retinal Optical Coherence Tomography (OCT) and OCT Angiography (OCTA) anomaly detection, existing unsupervised methods rely on visual feature distributions, reconstruction residuals, or encoder-decoder discrepancies, making anomaly scores depend on appearance-level deviations, whi...