{"ID":6537721,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11173","arxiv_id":"2607.11173","title":"When Depth Is Better Told Than Shown: Depth-Ordinal Prompting for Vision-Language Spatial Reasoning","abstract":"Vision-language models (VLMs) are expected to reason about physical space -- which object is closer, what lies behind what, and how objects are arranged in 3D -- yet they still struggle with such spatial judgments. A natural remedy is to show the model a depth map, but we find that this can make performance worse. We show that depth is not absent: it reaches the language model, but becomes difficult to access for downstream reasoning, while rendered pseudo-depth maps act as noisy auxiliary images that frozen VLMs cannot easily regulate. We propose Depth-Ordinal Prompting (DOP), a training-free method that converts monocular depth into a single question-targeted ordinal text cue at the queried objects, without adding a depth image, training a module, injecting features, or using labels. Our key finding is form dependence: the same depth signal can hurt when shown as an image but help when told as text.Across benchmarks, models, and depth estimators, DOP improves spatial reasoning when pseudo-depth provides reliable object-level ordering and remains largely neutral in strong original-image regimes. It is also competitive with the strongest training-free depth-prompting alternative while being simpler and more targeted.","short_abstract":"Vision-language models (VLMs) are expected to reason about physical space -- which object is closer, what lies behind what, and how objects are arranged in 3D -- yet they still struggle with such spatial judgments. A natural remedy is to show the model a depth map, but we find that this can make performance worse. We s...","url_abs":"https://arxiv.org/abs/2607.11173","url_pdf":"https://arxiv.org/pdf/2607.11173v1","authors":"[\"Quynh Vo\",\"Phuc Dao\",\"Cong-Duy Nguyen\",\"Thong Nguyen\"]","published":"2026-07-13T07:13:01Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}