// 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 LLMs & Texto

AnchorVLA: Bridging Discrete Decisions and Continuous Trajectories for Vision-Language-Action Planning

arXiv:2607.03182v1 Announce Type: new Abstract: Autonomous driving planning requires translating navigation intent, traffic rules, dynamic interactions, and language instructions into executable continuous trajectories. Vision-Language-Action models have been introduced into driving planning to improve long-tail generalization, commonsense reasoning, high-level semantic understanding, and explainability. However, existing VLA planners mainly follow planning-head-based trajectory prediction or fu...

07.07.2026
Blog Robótica & RL

Embodied Operators and Benchmarking: Toward Reusable and Deployable Embodied Intelligence Systems

arXiv:2607.03283v1 Announce Type: new Abstract: Embodied intelligence systems require not only end-to-end policy models, but also reusable functional modules that transform multimodal observations, robot states, human demonstrations, and task contexts into structured representations, decisions, trajectories, control references, and system services. This work defines these modules as embodied operators and studies them as independent yet composable units in embodied intelligence pipelines. We cla...

07.07.2026
Blog LLMs & Texto

Criterion-Conditional In-Context Learning: Evaluating Criterion-Shift Adaptation in Vision-Language Models

arXiv:2607.02575v1 Announce Type: new Abstract: Vision-language models can perform new tasks without parameter updates through in-context learning (ICL), whose core mechanism is utilizing the support set for task induction. In the standard ICL setting, once the task is induced, its decision criterion remains fixed. However, in real-world applications, many tasks exhibit a stable high-level intent, while their decision criteria shift according to specific requirements. Thus, we introduce a new se...

07.07.2026
Blog Robótica & RL

TACO: TActile World Model as a Self-COrrector forScalable VLA Post-Training

arXiv:2607.02840v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown promising generalization in robotic manipulation, but they still struggle with contact-rich tasks, where minor contact perturbations can cause unrecoverable failures that are hard to detect from vision alone. Since these failures are localized rather than task-level semantic errors, tactile-aware corrective post-training offers an efficient way to improve recovery. However, scaling such supervision thr...

07.07.2026
Blog Multimodal

CoFEND: A Cross-Modal Fusion End-to-End Network for Cold-Start Drug-Drug Interaction Prediction

arXiv:2607.02928v1 Announce Type: new Abstract: Cold-start drug-drug interaction (DDI) prediction for new drugs is critical for minimizing unexpected adverse drug reactions. The key challenge is to capture similarity between new and known drugs. However, such similarity is closely associated with complex relationships and mechanisms among drugs, enzymes, transporters, molecular structures, and other biomedical entities. Existing methods have three limitations in capturing such similarity: (1) on...

07.07.2026
Blog LLMs & Texto

DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences

arXiv:2607.02551v1 Announce Type: new Abstract: Video multimodal large language models have made strong progress on open-ended video understanding, but they still lack precise local spatiotemporal perception. When two videos share almost the same global semantics and differ only in a short time span or a small region, current models often fail to find the change and provide reliable evidence. We propose DELTAVID, a verifiable proxy-task framework that enhances fine-grained spatiotemporal percept...

07.07.2026
Blog LLMs & Texto

Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation

arXiv:2607.02593v1 Announce Type: new Abstract: While knowledge distillation (KD) is widely adopted for training lightweight models by leveraging supervision from larger teacher models, relying solely on output token distributions has proven insufficient for compressing Multimodal Large Language Models (MLLMs). Since output tokens are a byproduct of the model attending to visual inputs, prior works have explored explicitly distilling attention to provide a direct supervisory signal. While promis...

07.07.2026
← anterior 20 / 39 próxima →
467 itens no radar