Multimodal

Blog LLMs & Texto

Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilities

arXiv:2607.27747v1 Announce Type: new Abstract: Large Vision Language Models have integrated reasoning capabilities, elevating cognitive performance to new levels. However, existing evaluations either focus solely on perception or rely on specific domains such as maths or coding. Evaluation for reasoning capabilities that align with an open-world environment is still required, especially one that considers perception and reasoning jointly. To bridge this gap, we propose to evaluate LVLMs by expl...

31.07.2026

Blog Geração de Imagem

MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

arXiv:2607.27616v1 Announce Type: new Abstract: Text-to-image and personalized editing models now synthesize high-fidelity single-subject images with ease. Yet placing multiple named people into shared contact actions such as embrace, carry, or grapple still exposes major failures: fused limbs, invented extremities, and interpenetrating bodies. Existing evaluations largely overlook these anatomical and geometric issues, and VLM-as-a-judge checklists often saturate on Interaction while the errors...

31.07.2026

Blog LLMs & Texto

MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models

arXiv:2607.27637v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or shifted contexts. A reliable MLLM should refuse truly out-of-context (OOC) questions with subject-level context shifts while still answering shifted in-context (Shifted IC) questions with non-subject context shifts. Existing benchmarks mainly target OOC or visually unanswerable questions, but overlook...

31.07.2026

Blog Robótica & RL

RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy

arXiv:2607.27782v1 Announce Type: new Abstract: Flow-matching Vision-Language-Action (VLA) policies have shown strong potential for robotic manipulation but often suffer from compounding errors caused by distribution shifts during deployment. While offline reinforcement learning (RL) provides a practical way to improve deployed policies using rollout data, existing methods either ignore failure data or exploit it only at the trajectory level, resulting in low learning efficiency and persistent e...

31.07.2026

Blog LLMs & Texto

ClinLens: Towards Long-Horizon Coding Agents for Longitudinal Multimodal Clinical Data Science

arXiv:2607.26155v1 Announce Type: new Abstract: Clinical data-science agents must transform heterogeneous longitudinal records into auditable analyses, yet existing benchmarks largely isolate medical question answering, structured-table reasoning, or generic scientific repositories. We introduce CLINLENS, a benchmark of 200 executable tasks over five linked MIMIC resources spanning structured electronic health records, notes, electrocardiograms, chest radiographs, and echocardiograms. A 4 x 5 ta...

31.07.2026

Blog LLMs & Texto

Inference-Time Agentic Decision Rules Beat Longer Evolving Search for Multi-Image Medical Reasoning

arXiv:2607.27564v1 Announce Type: new Abstract: Multi-image medical VQA is not merely a prompt-length problem; it is a fundamental challenge of agentic decision-making. Medical vision-language agents must aggregate evidence across ordered images, remain robust to answer-order perturbations, and avoid overfitting to noisy search-time feedback. We study MedFrameQA through a controlled comparison of five inference-time agentic strategies, optimized using the same high-budget ShinkaEvolve configurat...

31.07.2026

Blog LLMs & Texto

JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles

arXiv:2607.27670v1 Announce Type: new Abstract: Jigsaw puzzle solving requires jointly reasoning about visual content and geometric constraints, yet existing benchmarks use rectangular cuts that create ambiguous ground truth in texture-repeated regions. We introduce \textit{\ours{}}, a benchmark with tab-and-blank interlocking pieces where geometric constraints provide strong local compatibility requirements that, combined with visual content, yield unambiguous ground truth. Across 95K instances...

31.07.2026

Blog LLMs & Texto

CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games

arXiv:2607.26393v1 Announce Type: new Abstract: Social deduction games (SDGs) such as Werewolf have become challenging testbeds for AI agents. These games require complex social skills such as reasoning, deception, and collaboration. While recent advances in large language models (LLMs) have driven significant progress in SDG agents, current approaches are predominantly text-based, overlooking the multimodal nature that is fundamental to human social interaction. To bridge this gap, we introduce...

31.07.2026

Blog LLMs & Texto

Position, Not Provenance: Separating Reasoning Mediation from Sycophancy in Medical Vision-Language Models

arXiv:2607.27304v1 Announce Type: new Abstract: Medical vision-language models (VLMs) generate chain-of-thought (CoT) reasoning before answering clinical questions, but whether this reasoning causally influences predictions remains unclear. We present CoT-Mediate, a behavioral framework that perturbs a single clinically meaningful attribute within a model's own generated reasoning and measures whether the resulting prediction follows the edited reasoning. Our framework combines a dual-arm protoc...

31.07.2026

Blog Geração de Imagem

AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes

arXiv:2607.27393v1 Announce Type: new Abstract: Hateful memes are a growing form of multimodal online harm, where hostile intent is often conveyed through the joint interpretation of images, text, cultural references, and implicit targets. While hateful meme detection has advanced in high-resource languages, Arabic remains underexplored, with existing meme resources focusing mainly on propaganda or coarse harmful-content labels. We introduce AHA-Memes (Arabic HAteful Memes), which is, to our kno...

31.07.2026

Blog Robótica & RL

CG-World: A Large-Scale World-State Dataset and Protocol for World Models

arXiv:2607.26452v1 Announce Type: new Abstract: World models must learn the joint dynamics of states, actions, events, and observations, yet existing video, robotics, and simulation datasets usually capture only part of this structure. We introduce CG-World, a large-scale world-state dataset and protocol derived from industrial computer graphics production pipelines. CG-World explicitly records intermediate states, including multimodal semantics, spatial structure, skeletal and controller states...

31.07.2026

Blog Multimodal

Calibrate Before Reason: Robust Visual Token Reduction against Semantic Drift in VLMs

arXiv:2607.27700v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) suffer from prohibitive inference overhead due to long sequences of visual tokens. However, existing visual token reduction methods mainly improve efficiency by pruning or compressing redundant tokens without examining whether the resulting representation remains semantically consistent with the original representation. Mapping the original N-token visual sequence to K tokens may discard, dilute, or misassign cri...

31.07.2026