Cover Image

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Jingli, Zhu, Chenming, Xu, Runsen, Mao, Xiaohan, Liu, Xihui, Wang, Tai, Pang, Jiangmiao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations
by: Lyu, Ruiyuan, et al.
Published: (2024)

LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness
by: Zhu, Chenming, et al.
Published: (2024)

MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
by: Yang, Sihan, et al.
Published: (2025)

MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence
by: Lin, Jingli, et al.
Published: (2025)

ChangingGrounding: 3D Visual Grounding in Changing Scenes
by: Hu, Miao, et al.
Published: (2025)

G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
by: Hu, Wenbo, et al.
Published: (2025)

PointLLM: Empowering Large Language Models to Understand Point Clouds
by: Xu, Runsen, et al.
Published: (2023)

VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization
by: Yang, Sihan, et al.
Published: (2025)

VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
by: Xu, Runsen, et al.
Published: (2024)

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
by: He, Yuping, et al.
Published: (2025)

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling
by: Wei, Meng, et al.
Published: (2025)

ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities
by: Zhu, Chenming, et al.
Published: (2024)

Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
by: Huang, Haifeng, et al.
Published: (2023)

Grounded 3D-LLM with Referent Tokens
by: Chen, Yilun, et al.
Published: (2024)

InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
by: Zhong, Weipeng, et al.
Published: (2025)

OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition
by: Chen, Tongjia, et al.
Published: (2023)

Unified Human-Scene Interaction via Prompted Chain-of-Contacts
by: Xiao, Zeqi, et al.
Published: (2023)

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
by: Zhang, Zixin, et al.
Published: (2025)

STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?
by: Li, Yun, et al.
Published: (2025)

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
by: Meng, Jiahao, et al.
Published: (2026)

Towards Latency-Aware 3D Streaming Perception for Autonomous Driving
by: Peng, Jiaqi, et al.
Published: (2025)

ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?
by: Yang, Liu, et al.
Published: (2025)

InstructionBench: An Instructional Video Understanding Benchmark
by: Wei, Haiwan, et al.
Published: (2025)

ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting
by: Zhu, Ruijie, et al.
Published: (2025)

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes
by: Chen, Xiao, et al.
Published: (2025)

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
by: Zhu, Muzhi, et al.
Published: (2025)

EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
by: Pei, Baoqi, et al.
Published: (2025)

MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs
by: Xu, Yunqiu, et al.
Published: (2024)

Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM
by: Huang, Haifeng, et al.
Published: (2026)

Language-to-Space Programming for Training-Free 3D Visual Grounding
by: Mi, Boyu, et al.
Published: (2025)

StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
by: Lin, Junming, et al.
Published: (2024)

AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding
by: Wang, Yonghui, et al.
Published: (2024)

On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding
by: Pang, Zhanzhong, et al.
Published: (2026)

PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines
by: Wang, ZiDong, et al.
Published: (2024)

Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos
by: Tang, Yuqi, et al.
Published: (2026)

VER-Bench: Evaluating MLLMs on Reasoning with Fine-Grained Visual Evidence
by: Qiang, Chenhui, et al.
Published: (2025)

MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs
by: Liu, Jiyao, et al.
Published: (2025)

IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering
by: Liu, Parker, et al.
Published: (2025)

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
by: Wang, Qi, et al.
Published: (2025)

3D Spatial Understanding in MLLMs: Disambiguation and Evaluation
by: Chang, Chun-Peng, et al.
Published: (2024)