Multimodal — Radar de IA

Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach

arXiv:2607.15661v1 Announce Type: new Abstract: Large vision-language models (LVLMs) can be adapted to specialized medical imaging tasks via parameter-efficient fine-tuning approaches such as low-rank adaptation (LoRA), leading to a growing ecosystem of expert models tailored to specific imaging modalities and clinical scenarios. However, deploying multiple expert LVLMs in practice incurs substantial computational and operational overhead. Model merging provides a promising solution by consolida...

20.07.2026

Blog Robótica & RL

AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning

arXiv:2607.15714v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models excel at end-to-end robotic manipulation but struggle with out-of-distribution (OOD) generalization when familiar sub-tasks are recombined in unseen configurations. We identify two mutually reinforcing failure modes: \emph{trajectory overfitting}, where models overfit to holistic trajectory patterns rather than compositional sub-skill semantics; and \emph{perceptual shortcut}, where action tokens over-rely on wri...

20.07.2026

Blog LLMs & Texto

ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning

arXiv:2607.16131v1 Announce Type: new Abstract: Multimodal Scientific Claim Verification (MSCV) requires models to verify scientific claims using visually grounded evidence from papers, including figures, tables, charts, and textual context. However, existing methods often fail because they struggle to locate decisive visual evidence, accurately read structured scientific visuals, and integrate multimodal observations into reliable reasoning. We introduce ToolSciVer, the first tool-augmented fra...

20.07.2026

Blog LLMs & Texto

Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning

arXiv:2607.15374v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) ground whole objects well from free-form language queries, but they struggle when the query names a part rather than the object. We trace this to a missing object-part hierarchy, since parts are localized in the same single step used for objects. We propose Object-Part Hierarchical Reflective Grounding (OP-HRG), a coarse-to-fine reasoning-guided grounding strategy that first localizes the parent object and t...

20.07.2026

Blog LLMs & Texto

SkillNav: Score-Level Skill Intervention for Zero-Shot Object Goal Navigation

arXiv:2607.15758v1 Announce Type: new Abstract: Vision-Language Model (VLM) agents have advanced zero-shot object-goal navigation, yet single-frame reasoning leaves them without the cross-step behavioral awareness an embodied navigator requires, producing recurring failures such as dead-end stalls, in-room loops, and circuitous approaches to detected targets. Prompt-based remedies inflate token budgets across multi-submodule episodes and still struggle to encode inherently spatial signals such a...

20.07.2026

Blog LLMs & Texto

When Can Test-Time Adaptation Help Zero-Shot CT Vision-Language Models?

arXiv:2607.15556v1 Announce Type: new Abstract: 3D CT vision-language models (VLMs) classify abnormalities from text prompts in a zero-shot manner, enabling cross-institution deployment where labels are scarce and clinical tasks shift faster than supervised models can be retrained. A real CT scan, however, typically contains several co-occurring abnormalities, and the reliability of zero-shot multi-label prediction under distribution shift remains poorly understood. Test-time adaptation (TTA) up...

20.07.2026

Blog Visão Computacional

Training-Free Open-Vocabulary 3D Point-Cloud Segmentation on the Generalized Few-Shot Benchmark

arXiv:2607.15331v1 Announce Type: new Abstract: Generalized few-shot 3D point-cloud segmentation (GFS-PCS) asks a model to segment a scene into many base classes seen at training time and a set of novel classes. The state of the art reaches novel classes by reconciling a dense but noisy 3D vision-language prior with the few-shot support, but it pays for this with base 3D labels, per-episode training, and the support annotations themselves. We ask how far the same reconciliation can go with none ...

20.07.2026

Blog Multimodal

SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery

arXiv:2607.16038v1 Announce Type: new Abstract: Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research state. We present SciForge, a multimodal research-native AI workbench that reserves the graphical interface for human judgment while search, parsing, model routing, workflow execution,...

20.07.2026

Blog LLMs & Texto

Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes

arXiv:2607.15442v1 Announce Type: new Abstract: Internet memes intertwine visual cues, textual content, and cultural context, making them particularly challenging to interpret in scenarios where humor, sarcasm, and harmful intent coexist. These complexities highlight the need for explainable meme understanding systems that can provide reliable and structured reasoning to support both accurate classification and human interpretability. However, existing multimodal classifiers either overlook thes...

20.07.2026

Blog LLMs & Texto

Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors

arXiv:2607.15689v1 Announce Type: new Abstract: Understanding long videos with multimodal large language models (MLLMs) requires selecting a compact set of frames from thousands of candidates, yet identifying the right frames seemingly requires understanding the video first. We resolve this circular dependency with a simple observation: cross-modal attention at validation-selected extraction layers in MLLMs already provides query-relevant frame evidence without requiring autoregressive generatio...

20.07.2026

Blog LLMs & Texto

Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models

arXiv:2607.15565v1 Announce Type: new Abstract: Where should the question go in a vision-language model (VLM) prompt: before the image or after it? Intuition says before: knowing what is asked should tell the model where to look. Yet across visual question answering benchmarks, question-first prompting consistently underperforms the image-first ordering recommended for frontier VLMs, a phenomenon we term the question-first paradox. We trace the paradox to a conflict between two stages of VLM com...

20.07.2026

Blog LLMs & Texto

MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

arXiv:2607.15592v1 Announce Type: new Abstract: Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such a design forces the denoiser to simultaneously perform relation-dependent cue selection, cross-modal semantic alignment, and structure-aware entity generation, which introduces noisy and semantically inconsistent conditions for diff...

20.07.2026