Pith. sign in

REVIEW 20 cited by

STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?

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

arxiv 2503.23765 v6 pith:3ROOSSE4 submitted 2025-03-31 cs.CV

classification cs.CV
keywords mllmsspatial-temporalunderstandingprecisetasksbenchmarkevaluatemodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The use of Multimodal Large Language Models (MLLMs) as an end-to-end solution for Embodied AI and Autonomous Driving has become a prevailing trend. While MLLMs have been extensively studied for visual semantic understanding tasks, their ability to perform precise and quantitative spatial-temporal understanding in real-world applications remains largely unexamined, leading to uncertain prospects. To evaluate models' Spatial-Temporal Intelligence, we introduce STI-Bench, a benchmark designed to evaluate MLLMs' spatial-temporal understanding through challenging tasks such as estimating and predicting the appearance, pose, displacement, and motion of objects. Our benchmark encompasses a wide range of robot and vehicle operations across desktop, indoor, and outdoor scenarios. The extensive experiments reveals that the state-of-the-art MLLMs still struggle in real-world spatial-temporal understanding, especially in tasks requiring precise distance estimation and motion analysis.

Discussion (0). Sign in to comment.

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    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.

  2. CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    Proposes Spatial Narrative Score (SNS) evaluation for VLMs' camera motion understanding and introduces CaMo model achieving consistent performance on SNS and direct QA.

  3. ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    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.

  4. SCP: Spatial Causal Prediction in Video

    cs.CV 2026-03 unverdicted novelty 7.0 of 10

    SCP defines a new benchmark task for predicting spatial causal outcomes beyond direct observation and shows that 23 leading models lag far behind humans on it.

  5. SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition

    cs.AI 2025-11 unverdicted novelty 7.0 of 10

    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.

  6. SpaceR: Reinforcing MLLMs in Video Spatial Reasoning

    cs.CV 2025-04 unverdicted novelty 7.0 of 10

    SpaceR uses a new verifiable dataset and map-imagination-augmented RLVR to reach SOTA spatial reasoning accuracy in MLLMs, exceeding GPT-4o on VSI-Bench.

  7. Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    ReRe boosts open-source MLLMs on spatial reasoning benchmarks VSI-Bench and STI-Bench to rival proprietary SOTA by using a two-phase Reason then Re-reason process with Geometry-to-Video novel view synthesis.

  8. Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    GASP injects geometric priors into VLMs via a deep-supervised correspondence head trained on video point correspondences and depth consistency, raising internal matching accuracy and delivering gains on spatial benchm...

  9. Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    Q-GeoMem uses question-guided scoring to maintain a Fine-Grained Context Bank and Semantic-Geometric Evidence Bank, achieving SOTA on VSI-Bench and VSTI-Bench.

  10. Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    Flat-Pack Bench is a new evaluation suite that shows state-of-the-art LVLMs perform poorly on nuanced spatio-temporal reasoning required for furniture assembly videos.

  11. LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    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.

  12. SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning

    cs.CV 2026-03 unverdicted novelty 6.0 of 10

    SpatialStack improves 3D spatial reasoning in vision-language models by stacking and synchronizing multi-level geometric features with the language backbone.

  13. $M^3-Verse$: A "Spot the Difference" Challenge for Large Multimodal Models

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A new benchmark tests whether large multimodal models can compare paired 'before and after' videos to detect scene changes, and finds current models perform near random.

  14. SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving

    cs.CV 2025-12 conditional novelty 6.0 of 10

    SpaceDrive replaces textual coordinate tokens with shared 3D positional encodings in a VLM driving planner, achieving state-of-the-art open-loop planning on nuScenes and 78.02 Driving Score on Bench2Drive.

  15. SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving

    cs.CV 2025-12 conditional novelty 6.0 of 10

    SpaceDrive integrates 3D positional encodings derived from depth and ego-states into VLMs, replacing digit tokens to improve spatial reasoning and trajectory regression in autonomous driving.

  16. Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

    cs.CV 2025-05 unverdicted novelty 6.0 of 10

    Spatial-MLLM adds a 3D spatial encoder initialized from a visual geometry model and space-aware frame sampling to MLLMs to improve spatial understanding and reasoning from purely 2D visual inputs.

  17. Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

    cs.CV 2025-05 unverdicted novelty 6.0 of 10

    Spatial-MLLM boosts MLLM spatial intelligence from 2D inputs via dual encoders initialized from geometry models plus space-aware sampling, claiming state-of-the-art results.

  18. LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    Presents LongSpace-Bench benchmark and LongSpace framework that chunks long videos, adds 3D structural cues, and builds layer-aware memory to improve spatial reasoning in multimodal LLMs.

  19. Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    Question-guided dual geometric memories with relevance-novelty utility reportedly reach state-of-the-art video spatial reasoning on two in-domain and five out-of-distribution benchmarks.

  20. The high-speed X-ray camera on AXIS: design and performance updates

    astro-ph.IM 2025-08 unverdicted novelty 4.0 of 10

    An X-ray camera design-update whose supporting full text is a different paper (RynnEC, an embodied AI model), leaving all camera performance claims unverified.

Pith tools