Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Langage Model

Vision Language Models Explained

Vision Language Models (Better, faster, stronger)

A Dive into Vision-Language Models

Accelerating Vision-Language Models: BridgeTower on Habana Gaudi2

Accelerating vision-language models with LFM2.5-VL-DSpark

Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs

The paper reports a submission to the SHROOM-Visions shared task, aiming to detect and classify hallucinated character spans in vision‑language model outputs across four languages. The authors use multiple fine‑tuned vision‑language models as independent annotators, combine their predictions via character‑level majority voting, and also investigate activation probes. Their method achieved first place in three of the four languages and consistently ranked on the podium for all languages and metrics, with analysis showing that model disagreement mirrors human annotator disagreement.

SmolVLM - small yet mighty Vision Language Model

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

Vision-Language Models are Fragile Multilingual Associators

arXiv:2608. 12333v1 Announce Type: cross Abstract: Vision-language models must associate visual entities with textual attributes.

SigLIP 2: A better multilingual vision language encoder