Cover Image

Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jeon, Yerim, Lee, Miso, Moon, WonJun, Heo, Jae-Pil
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization
by: Lee, Miso, et al.
Published: (2026)

Temporally Consistent Long-Term Memory for 3D Single Object Tracking
by: Yoo, Jaejoon, et al.
Published: (2026)

From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning
by: Seong, Hyun Seok, et al.
Published: (2026)

Selective Contrastive Learning for Weakly Supervised Affordance Grounding
by: Moon, WonJun, et al.
Published: (2025)

Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning
by: Moon, WonJun, et al.
Published: (2026)

Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding
by: Moon, WonJun, et al.
Published: (2023)

VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting
by: Kang, Seunggu, et al.
Published: (2023)

Activating Self-Attention for Multi-Scene Absolute Pose Regression
by: Lee, Miso, et al.
Published: (2024)

Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentation
by: Seong, Hyun Seok, et al.
Published: (2024)

Temporal Alignment-Free Video Matching for Few-shot Action Recognition
by: Lee, SuBeen, et al.
Published: (2025)

Auxiliary Descriptive Knowledge for Few-Shot Adaptation of Vision-Language Model
by: Lee, SuBeen, et al.
Published: (2025)

Mitigating Background Shift in Class-Incremental Semantic Segmentation
by: Park, Gilhan, et al.
Published: (2024)

Mutually-Aware Feature Learning for Few-Shot Object Counting
by: Jeon, Yerim, et al.
Published: (2024)

Long-term Pre-training for Temporal Action Detection with Transformers
by: Kim, Jihwan, et al.
Published: (2024)

Boundary-Recovering Network for Temporal Action Detection
by: Kim, Jihwan, et al.
Published: (2024)

White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentation
by: Im, Jiyun, et al.
Published: (2025)

Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation
by: Lee, ByeongCheol, et al.
Published: (2026)

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval
by: Moon, WonJun, et al.
Published: (2025)

Prediction-Feedback DETR for Temporal Action Detection
by: Kim, Jihwan, et al.
Published: (2024)

Mitigating Semantic Collapse in Partially Relevant Video Retrieval
by: Moon, WonJun, et al.
Published: (2025)

GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats
by: Hyun, Sangeek, et al.
Published: (2024)

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
by: Hur, Jiwan, et al.
Published: (2024)

Noise-free Optimization in Early Training Steps for Image Super-Resolution
by: Lee, MinKyu, et al.
Published: (2023)

SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning
by: Hwang, Chan Yeong, et al.
Published: (2026)

Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer
by: Chung, Jiwoo, et al.
Published: (2023)

Cross-scale Aligned Supervision for Training GANs
by: Hyun, Sangeek, et al.
Published: (2026)

Auto-Encoded Supervision for Perceptual Image Super-Resolution
by: Lee, MinKyu, et al.
Published: (2024)

PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting
by: Seo, Kangmin, et al.
Published: (2026)

Scalable GANs with Transformers
by: Hyun, Sangeek, et al.
Published: (2025)

SpatialReasoner: Active Perception for Large-Scale 3D Scene Understanding
by: Zheng, Hongpei, et al.
Published: (2025)

Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement
by: Jun, Jinyoung, et al.
Published: (2024)

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes
by: Liu, Tianhui, et al.
Published: (2026)

SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
by: Huang, Jiaxin, et al.
Published: (2025)

Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
by: Li, Qiming, et al.
Published: (2025)

Analyzing the Training Dynamics of Image Restoration Transformers: A Revisit to Layer Normalization
by: Lee, MinKyu, et al.
Published: (2025)

SAM-Guided Masked Token Prediction for 3D Scene Understanding
by: Chen, Zhimin, et al.
Published: (2024)

Diversity-aware Channel Pruning for StyleGAN Compression
by: Chung, Jiwoo, et al.
Published: (2024)

Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning
by: Chen, Jiahua, et al.
Published: (2026)

Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation
by: Park, Suho, et al.
Published: (2025)

SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
by: Ma, Chenyang, et al.
Published: (2024)