BBox DocVQA: A Large Scale Bounding Box Grounded Dataset for Enhancing Reasoning in Document Visual Question Answer

A new framework named HazardForge has been introduced to enhance the evaluation of Vision Language Models (VLMs) in autonomous vehicles and mobile systems, addressing the inadequacy of existing benchmarks in simulating diverse hazardous scenarios. This framework includes the MovSafeBench, a benchmark with 7,254 images and corresponding question-answer pairs across 13 object categories.

A new study has introduced a subject decoupling framework for zero-shot distracted driver detection using Vision Language Models (VLMs). This approach aims to improve the accuracy of detecting driver distractions by separating appearance factors from behavioral cues, addressing a significant limitation in existing VLM-based systems.

A theoretical analysis of decentralization in autoregressive generation has been presented, introducing the Decentralized Discrete Flow Matching objective, which expresses probability generating velocity as a linear combination of expert flows. Experiments demonstrate the equivalence between decentralized and centralized training settings for multimodal language models, specifically comparing LLaVA and InternVL 2.5-1B.