REVIEW 5 cited by
Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Despite recent advances demonstrating vision-language models' (VLMs) abilities to describe complex relationships in images using natural language, their capability to quantitatively reason about object sizes and distances remains underexplored. In this work, we introduce a manually annotated benchmark, Q-Spatial Bench, with 271 questions across five categories designed for quantitative spatial reasoning and systematically investigate the performance of state-of-the-art VLMs on this task. Our analysis reveals that reasoning about distances between objects is particularly challenging for SoTA VLMs; however, some VLMs significantly outperform others, with an over 40-point gap between the two best performing models. We also make the surprising observation that the success rate of the top-performing VLM increases by 19 points when a reasoning path using a reference object emerges naturally in the response. Inspired by this observation, we develop a zero-shot prompting technique, SpatialPrompt, that encourages VLMs to answer quantitative spatial questions using reference objects as visual cues. By instructing VLMs to use reference objects in their reasoning paths via SpatialPrompt, Gemini 1.5 Pro, Gemini 1.5 Flash, and GPT-4V improve their success rates by over 40, 20, and 30 points, respectively. We emphasize that these significant improvements are obtained without needing more data, model architectural modifications, or fine-tuning.
Forward citations
Cited by 5 Pith papers
-
It's Time to Get It Right: Improving Analog Clock Reading and Clock-Hand Spatial Reasoning in Vision-Language Models
TickTockVQA (12k real-world clocks) plus Swap-DPO lifts Llama-3.2-11B full-time analog clock accuracy from 1.41% to 46.22%, far above synthetic-data baselines.
-
Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks
A new contrastive real-image benchmark shows most vision-language models fail spatial relation tasks, while chain-of-thought reasoning models approach human-level accuracy.
-
AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making
AntiGrounding lifts candidate robot trajectories into the VLM's visual space via multi-view rendering and structured VQA, and reports 57.5% average success across eight manipulation tasks, beating three intermediate-r...
-
TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models
Introduces a 700-pair benchmark for temporal causal reasoning in VLMs, revealing large open-source vs. closed-source gaps and strong position bias.
-
SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization
A view-consistency reward built from mirror-flipped images lifts Qwen2.5-VL-3B from 21.8% to 58.4% success on the Q-Spatial++ spatial benchmark.
Discussion (0). Continue with ORCID to comment.