// 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

Mitigating Class-Tail Undercoverage in Medical Vision-Language Models under Clinical Shift

arXiv:2607.28696v1 Announce Type: new Abstract: Medical vision-language models (VLMs) can retain high observed marginal coverage after clinical shift while substantially under-covering an individual disease class. The affected class varies with acquisition protocol and backbone geometry, so source prevalence does not reliably reveal the failure. Existing localized and tail-aware conformal methods respectively adapt to test neighborhoods and source-frequency tails, leaving held-out class-wise cov...

03.08.2026
Blog LLMs & Texto

CAER: Conflict-Aware Evidence Routing with Dual Prefix Experts for Multimodal Large Language Models

arXiv:2607.28991v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in multimodal understanding and generation. However, when textual inputs conflict with visual evidence, they still suffer from hallucinations and produce responses inconsistent with visual content. Existing approaches mainly rely on decoding strategies, additional training, verification methods, or prompting techniques, but often lack fine-grained conflict localizati...

03.08.2026
Blog Robótica & RL

WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning

arXiv:2607.29613v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training of Vision-Language-Action (VLA) models has shown strong promise for robotic manipulation. Among RL methods, critic-based approaches rely on a value estimator that predominantly operates on single-frame observations or single-frame VLM backbone latents, which is a fundamental mismatch with the partially observable nature of robot control. A naive approach to incorporate observation history into the critic in...

03.08.2026
Blog Multimodal

MMFGU: Multimodal Federated Graph Unlearning

arXiv:2607.28708v1 Announce Type: new Abstract: Multimodal federated graph learning enables clients to collaboratively train graph models over structural, textual, and visual signals without sharing private local data. However, the presence of heterogeneous multimodal content also makes unlearning requests more frequent and fine-grained: users may delete accounts or interactions, remove a particular image or text while retaining the associated entity, or revoke the learned correspondence between...

03.08.2026
Blog Multimodal

FibVLA: An Efficient Temporal Vision-Language-Action Model with Fibonacci Sampling

arXiv:2607.29596v1 Announce Type: new Abstract: Vision-language-action models (VLAs), which leverage the cognition of multimodal information to infer physical-world actions, provide a generalized solution for embodied AI applications. Conventional VLAs usually concentrate on current digital cognition. While some efforts are made to enhance VLAs' reasoning capabilities by capturing temporal information, encoding the long-context history causes an efficiency-decreasing issue. To reconcile the conf...

03.08.2026
Blog Dados & Embeddings

ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding

arXiv:2607.28751v1 Announce Type: new Abstract: Universal multimodal embedding (UME) maps heterogeneous multimodal inputs into a shared embedding space. Existing UME models either form embeddings through single forward encoding or add computation through explicit rationale tokens and latent autoregressive states. Although token expansion can improve complex matching, serial generation increases retrieval latency and makes the final embedding depend on generated intermediate states. This raises a...

03.08.2026
Blog LLMs & Texto

SAGP: Semantic Affordance-Guided Grasp Planning via Coarse-Zone VLM Reasoning

arXiv:2607.29374v1 Announce Type: new Abstract: Geometry-based grasp planners ensure physically valid grasps but ignore functional semantics, often generating grasps that are antipodal and collision-free yet practically inappropriate, for example, gripping a mug by its rim, a knife by the blade, or a bottle near its cap. These inconsistencies cause the downstream task to fail even when traditional grasp metrics are met. Existing vision-language model (VLM) approaches either depend on fine-graine...

03.08.2026
Blog LLMs & Texto

ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding

arXiv:2607.28678v1 Announce Type: new Abstract: Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing agentic memory approaches often discard fine-grained dentity cues under aggressive compression and segment-wise processing. They also rely heavily on vector similarity retrieval, which can surface semantically related yet identity-mismatched evidence, leading to...

03.08.2026
Blog LLMs & Texto

Visual Distribution Anchoring for Efficient Prompt Tuning

arXiv:2607.28967v1 Announce Type: new Abstract: Prompt tuning adapts vision--language models with few trainable parameters, but existing approaches trade off efficiency and adaptation: static textual prompts can overfit source classes, image-conditioned prompts add per-instance computation, and multimodal tuning modifies the visual branch. We propose VDA (Visual Distribution Anchoring), a training-free target adaptation framework that augments a frozen semantic classifier with class-level visual...

03.08.2026
Blog Multimodal

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights

arXiv:2607.27482v1 Announce Type: new Abstract: A temporally drifting data stream may pass through discrete regimes rather than changing continuously. We ask whether such regimes are recoverable from the weights of models trained on the stream, using a hidden Markov model (HMM) fit to the chronologically ordered trajectory of those weights. We study this question in two domains known to drift over time: multimodal misinformation detection, using the Fakeddit dataset; and sentiment analysis, usin...

31.07.2026
← anterior 2 / 39 próxima →
467 itens no radar