Metric-Bench introduces a new benchmark for Vision‑Language Models (VLMs) that focuses on metric‑spatial reasoning in indoor scenes by using in‑image reference objects with known dimensions. The accompanying MetricReasoner fine‑tuning recipe employs structured prompts and numerical rewards to implicitly learn 2D‑to‑3D mapping without camera intrinsics. Experiments show that this approach improves spatial metric understanding by 43.1 % over existing models and boosts downstream embodied tasks, while also delivering gains on general VLM benchmarks.
arXiv:2601. 19099v2 Announce Type: replace-cross Abstract: Vision--language models (VLMs) achieve strong performance on many multimodal benchmarks but remain brittle on spatial reasoning tasks that require aligning abstract overhead representations with egocentric views.
Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps.
arXiv:2608. 12220v1 Announce Type: cross Abstract: Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning.
arXiv:2604. 08991v3 Announce Type: replace-cross Abstract: Reliable embodied interaction in indoor environments requires agents to precisely localize small everyday objects from visual observations.
Vision-language models (VLMs) achieve strong semantic understanding but remain unreliable in metric spatial reasoning, particularly when queries require comparing multiple instances of the same object category. We study this problem through the Closest-Instance Distance Query (CIDQ), where a model must identify the nearest visible candidate to a unique reference object and estimate their gravity-aligned floor-plane distance.
MV-STRIDE is a Multi‑View hierarchical Spatial Reasoning dataset that models dependencies among perception, scene understanding, and contextual reasoning to support 3D spatial cognition. It introduces a QA generation pipeline that enforces cross‑view constraints, producing multi‑level reasoning tasks with chain‑of‑thought supervision. Experiments show that training on MV‑STRIDE yields state‑of‑the‑art performance on multi‑view spatial benchmarks, enabling MLLMs to reason robustly across diverse viewpoints.
arXiv:2512. 24125v3 Announce Type: replace-cross Abstract: General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action execution, a combination that remains challenging for existing Vision-Language-Action (VLA) models.
SceneTeract is a verification interface that separates semantic action understanding from physical feasibility in indoor 3D scenes. It decomposes activities into atomic actions and performs explicit geometric checks to determine executability, providing diagnostic traces for failures. The system reveals widespread functional and accessibility issues in synthetic scenes, shows that existing VLMs over‑predict action feasibility, and improves VLM performance through post‑training with verifier feedback, with benefits that generalize to real‑world scenes.
arXiv:2605.03927v3 Announce Type: replace Abstract: Vision-language models have demonstrated strong performance across robotic perception and instruction-following tasks. However, they still struggle...
MultihopSpatial is a new benchmark for Vision‑Language Models that focuses on multi‑hop, compositional spatial reasoning with queries ranging from 1 to 3 hops across varied spatial perspectives. It introduces the Acc@50IoU metric, which jointly evaluates answer selection and precise bounding‑box prediction, and provides a large‑scale training corpus, MultihopSpatial‑Train, to improve spatial intelligence. Evaluation of 37 state‑of‑the‑art VLMs shows that compositional spatial reasoning remains a significant challenge, and reinforcement learning fine‑tuning on the corpus boosts both intrinsic spatial reasoning and downstream embodied manipulation performance.
Mem2Ego introduces a vision‑language model for embodied navigation that combines global memory with egocentric visual inputs. By adaptively retrieving task‑relevant cues from a global memory module and aligning them with local perception, the framework improves spatial reasoning and decision‑making over long horizons. The method outperforms prior state‑of‑the‑art approaches on the HSSD and HM3D benchmarks and shows strong performance on a real robot.
The paper introduces FactoSR, a factorized reinforcement learning framework designed to improve spatial reasoning in Vision‑Language Models by addressing a dimensional mismatch between 2D visual inputs and the 3D+temporal nature of the physical world. FactoSR decomposes the reasoning task into three orthogonal geometric sub‑objectives—planar correspondence (XY), depth consistency (Z), and temporal reversibility (T)—and optimizes these constraints within a unified policy learning mechanism. Experiments on multi‑view and video benchmarks show that this decomposition yields significant performance gains, achieving a 5.9% improvement on VSI‑Bench and 4.5% on All‑Angles‑Bench.