This paper systematically studies the robustness of vision foundation models to common image perturbations, finding that most models are generally non-robust and proposing a fine-tuning method to impr…

The paper proposes VLM3, a simple, scalable method that demonstrates standard Vision Language Models (VLMs) can natively learn 3D understanding by focusing on architectural simplicity and specific dat…

This paper organizes embodied data sources for multimodal foundation models into a pyramid, focusing on real-robot, UMI-style, egocentric and exocentric, simulation, and general vision-language data.

The paper introduces NewtPhys, a novel 4D dataset of real-world scenes with dense physical annotations, to systematically evaluate and reveal the limitations of foundation models in low-level Newtonia…

The paper introduces MedPMC, a framework that transforms permissively licensed literature into high-fidelity infrastructure for medical multimodal models, resulting in improved performance on various…

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 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 argues that benchmarking Vision-Language Models (VLMs) for urban perception must treat human disagreement and non-response as key measurement outcomes, rather than assuming perfect consensus…

Zamba2-VL is a new suite of vision-language models built on the Zamba2 hybrid architecture, achieving state-of-the-art performance and significantly improved inference efficiency compared to leading T…

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

The paper evaluates the adversarial robustness of two open-source Vision-Language Models (LLaVA and Qwen2.5-VL) in a simulated e-commerce environment, finding that while LLaVA is vulnerable to gradien…

The paper addresses the challenge of multi-turn view planning for VLMs by proposing an iterative framework that uses self-exploration and view graph distillation, significantly improving planning perf…

The paper introduces VIABLE, the first benchmark for evaluating Vision-Language Models (VLMs) as judges for Visually Impaired Assistance (VIA), finding that current models are largely unreliable and p…

The paper introduces a comprehensive benchmark to test if physics foundation models learn generalizable dynamics, finding that their performance is highly conditional and not universally general.

This paper details the systematic construction and training of a high-performing Romanian Vision-Language Model (VLM), demonstrating that language-specific adaptation significantly boosts performance…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

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…

The paper introduces AFUN, a model that predicts both the location (functional mask) and the motion (3D curve) for robot interaction, aiming to create a generalizable foundation model for understandin…

This pilot study evaluates curator-guided multilingual art description using a small, on-premise VLM (Qwen2.5-VL-3B-Instruct) for German, Romanian, and Serbian, finding that language-specific adapters…

This paper systematically analyzes the high cross-architecture transferability of physical adversarial attacks on Vision-Language Models (VLMs) used in autonomous driving, demonstrating that attacks e…