Cover Image

Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Jiangyong, Jia, Baoxiong, Wang, Yan, Zhu, Ziyu, Linghu, Xiongkun, Li, Qing, Zhu, Song-Chun, Huang, Siyuan
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

SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes
by: Linghu, Xiongkun, et al.
Published: (2025)

3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding
by: Linghu, Xiongkun, et al.
Published: (2026)

LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning
by: Huang, Jiangyong, et al.
Published: (2025)

Multi-modal Situated Reasoning in 3D Scenes
by: Linghu, Xiongkun, et al.
Published: (2024)

An Embodied Generalist Agent in 3D World
by: Huang, Jiangyong, et al.
Published: (2023)

Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding
by: Wang, Yan, et al.
Published: (2025)

Unifying 3D Vision-Language Understanding via Promptable Queries
by: Zhu, Ziyu, et al.
Published: (2024)

SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
by: Liu, Yu, et al.
Published: (2024)

SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
by: Jia, Baoxiong, et al.
Published: (2024)

Lifting Unlabeled Internet-level Data for 3D Scene Understanding
by: Chen, Yixin, et al.
Published: (2026)

ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting
by: Liu, Yu, et al.
Published: (2025)

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models
by: Li, Puhao, et al.
Published: (2025)

VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video
by: Liu, Yu, et al.
Published: (2025)

PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI
by: Yang, Yandan, et al.
Published: (2024)

SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
by: Yang, Yandan, et al.
Published: (2025)

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
by: Zhu, Ziyu, et al.
Published: (2025)

Longitudinal Structure of Quark-Gluon Plasma Unveiled Through Nuclear Deformations
by: Zhang, Chunjian, et al.
Published: (2024)

Task-oriented Sequential Grounding and Navigation in 3D Scenes
by: Zhang, Zhuofan, et al.
Published: (2024)

LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
by: Lin, Yutang, et al.
Published: (2026)

MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans
by: Yu, Huangyue, et al.
Published: (2025)

Bayesian Evidential Learning for Few-Shot Classification
by: Linghu, Xiongkun, et al.
Published: (2022)

Learning a Unified Policy for Position and Force Control in Legged Loco-Manipulation
by: Zhi, Peiyuan, et al.
Published: (2025)

Learning Human-Humanoid Coordination for Collaborative Object Carrying
by: Du, Yushi, et al.
Published: (2025)

PhysPart: Physically Plausible Part Completion for Interactable Objects
by: Luo, Rundong, et al.
Published: (2024)

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes
by: Lu, Ruijie, et al.
Published: (2024)

FM SO.P: A Progressive Task Mixture Framework with Automatic Evaluation for Cross-Domain SOP Understanding
by: Huang, Siyuan, et al.
Published: (2026)

Sources of Radial Flow Fluctuations in the Quark-Gluon Plasma
by: Jia, Jiangyong
Published: (2025)

Imaging nuclei by smashing them at high energies: how are their shapes revealed after destruction?
by: Jia, Jiangyong
Published: (2025)

ARFlow: Human Action-Reaction Flow Matching with Physical Guidance
by: Jiang, Wentao, et al.
Published: (2025)

Spatial-Temporal Multi-Scale Quantization for Flexible Motion Generation
by: Wang, Zan, et al.
Published: (2025)

3D Vision and Language Pretraining with Large-Scale Synthetic Data
by: Yang, Dejie, et al.
Published: (2024)

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis
by: Huang, Haoming, et al.
Published: (2025)

Neural-Symbolic Recursive Machine for Systematic Generalization
by: Li, Qing, et al.
Published: (2022)

Symmetric-asymmetric collision comparison: disentangling nuclear structure and subnucleonic structure effects for small system flow
by: Huang, Shengli, et al.
Published: (2025)

Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
by: Wang, Zan, et al.
Published: (2024)

ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
by: Zhao, Yanpeng, et al.
Published: (2026)

Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
by: Chen, Honghao, et al.
Published: (2025)

ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models
by: Zhang, Jieyu, et al.
Published: (2024)

The Mists of Ramanna
by: Aung-Thwin, Michael A.
Published: (2020)

GWM: Towards Scalable Gaussian World Models for Robotic Manipulation
by: Lu, Guanxing, et al.
Published: (2025)