arXiv:2608.23074v1 Announce Type: new Abstract: Vision-language models (VLMs) can answer spatial questions, yet the mechanisms connecting object grounding to spatial reasoning remain poorly understoo...
arXiv:2606. 23763v1 Announce Type: cross Abstract: Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens.
Vision-language models (VLMs) can answer spatial questions, yet the mechanisms connecting object grounding to spatial reasoning remain poorly understood. It is underexplored whether spatial reasoning...
arXiv:2607. 03358v1 Announce Type: cross Abstract: We study how visual information is routed in vision-language models (VLMs).
arXiv:2610.17976v1 Announce Type: new Abstract: Do vision-language models use depth information to judge which object is closer, or rely on image-plane cues? We investigate this question through cont...
Vision-language models (VLMs) are increasingly evaluated on complex image and video understanding tasks, yet conventional metrics primarily assess final-answer quality and reveal little about how diff...
The paper introduces a causal and temporal evaluation framework for vision‑language models (VLMs) that tracks how visual input, question text, and generated prefixes influence autoregressive decoding. It defines three step‑indexed causal‑drive metrics—Visual Causal Drive (VCD), Question Causal Drive (QCD), and Prefix Causal Drive (PCD)—using a Structural Causal Model and interventions. Experiments on Qwen3‑VL‑8B‑Instruct and other datasets show a shift from early question and visual guidance to increased reliance on generated prefixes, and demonstrate that QCD and PCD reduce recovery error and improve bias detection.
arXiv:2603. 06054v2 Announce Type: replace-cross Abstract: The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long-tail scenarios.
arXiv:2603. 22278v2 Announce Type: replace-cross Abstract: Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to bind objects with their properties and spatial relations.
arXiv:2607. 12815v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extended when VLMs generate longer reasoning traces.
The study examines how Vision‑Language Models (VLMs) integrate visual evidence into language‑based decisions by applying layer‑wise causal interventions on video‑text attention pathways in a video‑based generative multiple‑choice setting. Findings reveal that visual information is primarily incorporated while processing candidate answer options, with nouns serving as key semantic anchors and verbs becoming important during temporal reasoning. The research also uncovers a distinct pattern in temporal reasoning, indicating that VLMs struggle to reconstruct sequential information across video frames, possibly due to linguistic biases in temporal expressions.
arXiv:2605.13156v2 Announce Type: replace Abstract: Vision-language models (VLMs) have demonstrated remarkable capabilities in bridging visual perception and natural language understanding, enabling...