A blank-image ablation test reveals that high probe accuracy on VLM spatial reasoning frequently reflects priors or inverted signs rather than image grounding, with horizontal grounded, vertical prior, and depth inverted.
hub Mixed citations
Viewspatial-bench: Evaluating multi-perspective spatial localization in vision-language models.ArXiv, abs/2505.21500
Mixed citation behavior. Most common role is background (62%).
30
Pith papers citing it
Background
62% of classified citations
hub tools
citation-role summary
background 5
baseline 1
dataset 1
method 1
citation-polarity summary
representative citing papers
P2R decouples perception from reasoning in VLMs via a two-stage process and PRA-GRPO alternating RL training, reporting gains such as 93.2% on V-Star for the 4B model over its Qwen3-VL backbone.
MindEdit-Bench introduces six spatial reasoning tasks from 120 private indoor photo triplets, with two new counterfactual editing tasks where VLMs score 8-31% against 81-97% human accuracy.
AirGroundBench is a new diagnostic benchmark exposing that MLLMs handle basic spatial perception but struggle with cross-view alignment, transformation reasoning, and embodied navigation under heterogeneous air-ground views.
A closed-loop self-evolving training system for spatial reasoning in MLLMs that iteratively generates QA pairs matched to the model's current capabilities via confidence feedback, achieving gains with an order of magnitude less data.
Astra couples an RL-trained VLM policy with a view-consistent Bagel-based world simulator to enable agentic imagination during spatial reasoning, yielding benchmark gains on MMSI-Bench and MindCube.
OVO-S-Bench provides 1680 human-annotated questions on 348 videos to measure streaming spatial intelligence in MLLMs across instantaneous perception, spatiotemporal tracking, spatial simulation, and allocentric mapping.
SpatialAct benchmark shows VLMs handle isolated spatial reasoning but fail to maintain coherent spatial beliefs and produce reliable actions in multi-turn 3D interactions, underperforming humans.
GAMSI is a dual-pathway Geometry-Aware MLLM using Metric-Structure Decoupled Queries and Expert-Guided Visual Grounding on RGB inputs alone, trained on a new 152k-sample MTS dataset to reach SOTA on seven spatial benchmarks.
A decoupled question-conditioned image editor trained via supervised imitation then VLM-reward enhancement improves MLLM visual reasoning Pass@1 by 4.6-5.5 points across models and tasks.
The Token Replacement Test shows VLMs keep most accuracy gains even after corrupting or replacing continuous thought token content, indicating the tokens are not used as information bottlenecks.
Proposes Spatial Narrative Score (SNS) evaluation for VLMs' camera motion understanding and introduces CaMo model achieving consistent performance on SNS and direct QA.
MLLMs display a large perception-reasoning gap on perspective-conditioned spatial reasoning tasks from omnidirectional images, with sharp accuracy drops on advanced tasks like egocentric rotation, though partial gains are possible via RL reward shaping.
ViSRA boosts MLLM 3D spatial reasoning performance by up to 28.9% on unseen tasks via a plug-and-play video-based agent that extracts explicit spatial cues from expert models without any post-training.
SiMing-Bench shows current MLLMs have weak agreement with physicians on procedural correctness in clinical videos, with intermediate step judgments remaining poor even when overall scores look acceptable.
Backward token warping in ViT-based MLLMs enables reliable reasoning from nearby viewpoints by preserving semantic coherence better than pixel-wise warping or fine-tuning baselines.
SpatialMosaic introduces a 2M-pair multi-view QA dataset and 1M-pair benchmark for MLLMs on spatial reasoning under partial visibility, plus a hybrid baseline that integrates 3D reconstruction models as geometry encoders.
SpatialBench creates a five-level framework and 15-task benchmark to measure hierarchical spatial reasoning in MLLMs, finding strong basic perception but weak symbolic reasoning, causal inference, and planning.
SatAgent is a UAV-satellite collaborative spatial reasoning model using geometric 3D encoding, multi-view alignment, and a new 130K dataset that reports 25.91% and 11.69% gains over general and specialized baselines.
S-Agent augments VLMs with spatial tools, scene and agent memory for evidence accumulation on multi-view and video tasks, and produces an 8B model via SFT on its own trajectories that beats same-scale baselines.
IPT supervision improves spatial reasoning in VLMs on perspective taking, path tracing, and multiview counting tasks, often outperforming textual chain-of-thought while remaining consistent with observed inputs.
ProSR adds a Counterfactual Invariance Penalty and a Tail Drift Penalty to shape VLM reasoning trajectories for better visual dependence and stability on spatial tasks.
GeoWeaver performs token-adaptive geometric grounding on visual tokens from a multi-level bank prior to language modeling to support better spatio-temporal reasoning.
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
citing papers explorer
-
LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.