arXiv subjects

Marc Lalonde

Publications and source records attributed to Marc Lalonde.

4 recordsLinked to original sources

arXiv2026

Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform

This project investigates whether recent Vision-Language-Action (VLA) models can be transferred from controlled research benchmarks to a real-world robotic platform, specifically a UR5e manipulator, in a reproducible and operationally meaningful manner. The work integrates real-robot data acquisition, dataset engineering (compatible with the RLDS format), and the fine-tuning and deployment of OpenVLA and OpenVLA-OFT models, with systematic validation of action representations and control interfaces. The project resulted in several foundational assets: (i) a complete real-robot data acquisition pipeline, (ii) a dataset conversion workflow aligned with RLDS standards, (iii) an initial fine-tuning and inference infrastructure for VLA models, and (iv) a structured set of experimental observations grounded in real-robot trials. These elements collectively establish a reproducible framework for evaluating learning-based manipulation systems beyond simulation. Empirically, the experiments reveal a consistent gap between promising offline indicators and unstable closed-loop behavior on the physical system: this gap cannot be attributed solely to model limitations, it is strongly influenced by action semantics, coordinate frame conventions, temporal alignment between modalities, image preprocessing consistency, and dataset coverage and quality. These observations lead to a key interpretation: the successful deployment of VLA systems in real-world settings depends less on incremental improvements in model capacity and more on precise control of the entire data-model-control pipeline. The project reframes VLA-based robotics from a primarily model-centric challenge to a system-level problem; it highlights the difficulty of running robust task execution on the real robot and provides a clear, experimentally grounded understanding of the conditions required for reliable deployment.

cs.RO↗

arXiv2026

DevPrompt: Deviation-Based Prompt Learning for One-Normal ShotImage Anomaly Detection

Few-normal shot anomaly detection (FNSAD) aims to detect abnormal regions in images using only a few normal training samples, making the task highly challenging due to limited supervision and the diversity of potential defects. Recent approaches leverage vision-language models such as CLIP with prompt-based learning to align image and text features. However, existing methods often exhibit weak discriminability between normal and abnormal prompts and lack principled scoring mechanisms for patch-level anomalies. We propose a deviation-guided prompt learning framework that integrates the semantic power of vision-language models with the statistical reliability of deviation-based scoring. Specifically, we replace fixed prompt prefixes with learnable context vectors shared across normal and abnormal prompts, while anomaly-specific suffix tokens enable class-aware alignment. To enhance separability, we introduce a deviation loss with Top-K Multiple Instance Learning (MIL), modeling patch-level features as Gaussian deviations from the normal distribution. This allows the network to assign higher anomaly scores to patches with statistically significant deviations, improving localization and interpretability. Experiments on the MVTecAD and VISA benchmarks demonstrate superior pixel-level detection performance compared to PromptAD and other baselines. Ablation studies further validate the effectiveness of learnable prompts, deviation-based scoring, and the Top-K MIL strategy.

cs.CV↗

arXiv2025

Effectiveness of Large Multimodal Models in Detecting Disinformation: Experimental Results

The proliferation of disinformation, particularly in multimodal contexts combining text and images, presents a significant challenge across digital platforms. This study investigates the potential of large multimodal models (LMMs) in detecting and mitigating false information. We propose to approach multimodal disinformation detection by leveraging the advanced capabilities of the GPT-4o model. Our contributions include: (1) the development of an optimized prompt incorporating advanced prompt engineering techniques to ensure precise and consistent evaluations; (2) the implementation of a structured framework for multimodal analysis, including a preprocessing methodology for images and text to comply with the model's token limitations; (3) the definition of six specific evaluation criteria that enable a fine-grained classification of content, complemented by a self-assessment mechanism based on confidence levels; (4) a comprehensive performance analysis of the model across multiple heterogeneous datasets Gossipcop, Politifact, Fakeddit, MMFakeBench, and AMMEBA highlighting GPT-4o's strengths and limitations in disinformation detection; (5) an investigation of prediction variability through repeated testing, evaluating the stability and reliability of the model's classifications; and (6) the introduction of confidence-level and variability-based evaluation methods. These contributions provide a robust and reproducible methodological framework for automated multimodal disinformation analysis.

cs.CV↗

arXiv2025

VLM Models and Automated Grading of Atopic Dermatitis

The task of grading atopic dermatitis (or AD, a form of eczema) from patient images is difficult even for trained dermatologists. Research on automating this task has progressed in recent years with the development of deep learning solutions; however, the rapid evolution of multimodal models and more specifically vision-language models (VLMs) opens the door to new possibilities in terms of explainable assessment of medical images, including dermatology. This report describes experiments carried out to evaluate the ability of seven VLMs to assess the severity of AD on a set of test images.

cs.CV↗