The paper introduces FBHM, a new benchmark for hateful memes, and proposes LSV, a steering vector method that significantly improves VLM performance by addressing the generalization gap.

The paper systematically evaluates concept-based explainability in MLLMs, finding that forcing models to generate formal explanations degrades predictive accuracy, suggesting that explaining is genuin…

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

The paper proposes FedSAP, a framework that stabilizes federated prototype learning by delaying global alignment and enforcing inter-class structure, significantly improving representation quality und…

GiPL proposes a novel two-branch framework combining iterative pseudo-label self-training and generative data augmentation to significantly improve Cross-Domain Few-Shot Object Detection by better uti…

The paper proposes a training-free framework, Visual Representation-Guided Video-LLM Reasoning, to perform composed video retrieval by using visual examples and text instructions, achieving strong per…

This paper presents an open-source computer vision pipeline for classifying vehicle body types from naturalistic roadway video.

The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensiti…

The paper introduces CAFOSat, a large-scale, strongly annotated, and infrastructure-aware dataset designed to improve the accuracy of mapping Concentrated Animal Feeding Operations (CAFOs) from high-r…

This paper introduces CFMME, a comprehensive Chinese financial multimodal benchmark, and evaluates current Large Vision-Language Models (LVLMs), finding that while state-of-the-art models perform mode…

FLORO is a multimodal geospatial foundation model that learns transferable remote sensing representations from a small, diverse corpus, achieving strong performance across various sensor types and res…

The paper argues that the standard FID metric is unreliable because its performance depends significantly on the geometric structure and density of the reference dataset, not just the sample quality.

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and im…

The paper introduces OmniMatBench, a comprehensive, human-calibrated multimodal reasoning benchmark covering 19 materials science subfields, revealing that current multimodal language models (MLLMs) h…

The paper introduces a structured benchmark (TGAD) showing that current text-guided anomaly detection models often overstate their language conditioning, as performance significantly degrades when the…