Image de couverture de livre

SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hwang, Chan Yeong, Choi, Miso, On, Sunghyun, Kim, Jinkyu, Lee, Jungbeom
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Toward Interactive Regional Understanding in Vision-Large Language Models
par: Lee, Jungbeom, et autres
Publié: (2024)

ReCo: Reminder Composition Mitigates Hallucinations in Vision-Language Models
par: Chytas, Sotirios Panagiotis, et autres
Publié: (2025)

It's Time to Get It Right: Improving Analog Clock Reading and Clock-Hand Spatial Reasoning in Vision-Language Models
par: Choi, Jaeha, et autres
Publié: (2026)

Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding
par: Jeon, Yerim, et autres
Publié: (2025)

Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization
par: Park, Jihwan, et autres
Publié: (2025)

MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model
par: Lee, Youngwan, et autres
Publié: (2026)

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models
par: Lee, Dong-Jae, et autres
Publié: (2026)

Style-Friendly SNR Sampler for Style-Driven Generation
par: Choi, Jooyoung, et autres
Publié: (2024)

Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding
par: Kwon, Mincheol, et autres
Publié: (2026)

MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing
par: Choi, Changho, et autres
Publié: (2025)

AT-SNN: Adaptive Tokens for Vision Transformer on Spiking Neural Network
par: Kang, Donghwa, et autres
Publié: (2024)

Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models
par: Jang, Jaeyun, et autres
Publié: (2026)

Activating Self-Attention for Multi-Scene Absolute Pose Regression
par: Lee, Miso, et autres
Publié: (2024)

Long-term Pre-training for Temporal Action Detection with Transformers
par: Kim, Jihwan, et autres
Publié: (2024)

How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads
par: Baek, Ingeol, et autres
Publié: (2025)

SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining
par: Song, Chull Hwan, et autres
Publié: (2024)

Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
par: Kim, Jihyo, et autres
Publié: (2024)

Negative-Guided Subject Fidelity Optimization for Zero-Shot Subject-Driven Generation
par: Shin, Chaehun, et autres
Publié: (2025)

Ultra-Light Test-Time Adaptation for Vision--Language Models
par: Kim, Byunghyun
Publié: (2025)

Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining
par: Jang, Hyeonseo, et autres
Publié: (2026)

From Tokens to Photons: Test-Time Physical Prompting for Vision-Language Models
par: Im, Boyeong, et autres
Publié: (2025)

Vision-Language Memory for Spatial Reasoning
par: Liu, Zuntao, et autres
Publié: (2025)

Adaptive Cache Enhancement for Test-Time Adaptation of Vision-Language Models
par: Nguyen, Khanh-Binh, et autres
Publié: (2025)

Just Add $100 More: Augmenting NeRF-based Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem
par: Chang, Mincheol, et autres
Publié: (2024)

PointCubeNet: 3D Part-level Reasoning with 3x3x3 Point Cloud Blocks
par: Kim, Da-Yeong, et autres
Publié: (2025)

DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models
par: Chae, Daewon, et autres
Publié: (2025)

SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models
par: Cheng, An-Chieh, et autres
Publié: (2024)

RNA: Video Editing with ROI-based Neural Atlas
par: Lee, Jaekyeong, et autres
Publié: (2024)

Stream and Query-guided Feature Aggregation for Efficient and Effective 3D Occupancy Prediction
par: Moon, Seokha, et autres
Publié: (2025)

Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation
par: Oh, Yeongtak, et autres
Publié: (2024)

Intriguing Properties of Large Language and Vision Models
par: Lee, Young-Jun, et autres
Publié: (2024)

Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models
par: Park, Minho, et autres
Publié: (2024)

Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain
par: Lee, Seulbi, et autres
Publié: (2026)

D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models
par: Han, Jisu, et autres
Publié: (2025)

IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation
par: Baek, Sunghyun, et autres
Publié: (2026)

Personalized OVSS: Understanding Personal Concept in Open-Vocabulary Semantic Segmentation
par: Park, Sunghyun, et autres
Publié: (2025)

Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers
par: Baek, Kanghyun, et autres
Publié: (2026)

Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation
par: Xu, Ming, et autres
Publié: (2024)

InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
par: Deng, Nianchen, et autres
Publié: (2025)

ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation
par: Kim, Suyoung, et autres
Publié: (2026)