Cover Image

360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tran, Huyen T. T., Nguyen, Van-Quang, Alferro, Farros, Liu, Kang-Jun, Okatani, Takayuki
Format:	Preprint
Published:	2026
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

LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing
by: Fu, Wingwa, et al.
Published: (2026)

TB-Bench: Training and Testing Multi-Modal AI for Understanding Spatio-Temporal Traffic Behaviors from Dashcam Images/Videos
by: Charoenpitaks, Korawat, et al.
Published: (2025)

Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models
by: Sun, Li, et al.
Published: (2024)

Rethinking Unsupervised Domain Adaptation for Semantic Segmentation
by: Wang, Zhijie, et al.
Published: (2022)

An Improved Method for Personalizing Diffusion Models
by: Zeng, Yan, et al.
Published: (2024)

Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction
by: Charoenpitaks, Korawat, et al.
Published: (2023)

Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360-Degree Firefighting Videos
by: Tiwari, Aditi, et al.
Published: (2025)

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension
by: Ouyang, Kun, et al.
Published: (2024)

Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images
by: Lu, Xiangyong, et al.
Published: (2024)

Machine Intelligence that Understands Visual and Linguistic Information and Interacts with Humans and Environments
by: Nguyen, Van Quang
Published: (2026)

MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval
by: Sogi, Naoya, et al.
Published: (2025)

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs
by: Yuan, Jiakang, et al.
Published: (2025)

360PanT: Training-Free Text-Driven 360-Degree Panorama-to-Panorama Translation
by: Wang, Hai, et al.
Published: (2024)

CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models
by: Nguyen, Quang-Binh, et al.
Published: (2025)

RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution
by: Zou, Han, et al.
Published: (2023)

Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability
by: Hosoya, Yusuke, et al.
Published: (2024)

Rethinking Annotation for Object Detection: Is Annotating Small-size Instances Worth Its Cost?
by: Hosoya, Yusuke, et al.
Published: (2024)

Rethinking Open-Set Object Detection: Issues, a New Formulation, and Taxonomy
by: Hosoya, Yusuke, et al.
Published: (2022)

KTVIC: A Vietnamese Image Captioning Dataset on the Life Domain
by: Pham, Anh-Cuong, et al.
Published: (2024)

CoReTab: Improving Multimodal Table Understanding with Code-driven Reasoning
by: Nguyen, Van-Quang, et al.
Published: (2026)

ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images
by: Pham, Huy Quang, et al.
Published: (2024)

Explore the Hallucination on Low-level Perception for MLLMs
by: Sun, Yinan, et al.
Published: (2024)

From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information
by: Jiao, Qirui, et al.
Published: (2024)

Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training
by: Liu, Anglin, et al.
Published: (2026)

Action-Agnostic Point-Level Supervision for Temporal Action Detection
by: Yoshida, Shuhei M., et al.
Published: (2024)

Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipeline
by: Zuo, Rui, et al.
Published: (2025)

FreeRet: MLLMs as Training-Free Retrievers
by: Zhu, Yuhan, et al.
Published: (2025)

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness
by: Tang, Yolo Y., et al.
Published: (2025)

MambaU-Lite: A Lightweight Model based on Mamba and Integrated Channel-Spatial Attention for Skin Lesion Segmentation
by: Nguyen, Thi-Nhu-Quynh, et al.
Published: (2024)

TF-SASM: Training-free Spatial-aware Sparse Memory for Multi-object Tracking
by: Nguyen-Quang, Thuc, et al.
Published: (2024)

LiteNeXt: A Novel Lightweight ConvMixer-based Model with Self-embedding Representation Parallel for Medical Image Segmentation
by: Tran, Ngoc-Du, et al.
Published: (2024)

Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
by: Kang, Caixin, et al.
Published: (2026)

Training-Free Reasoning and Reflection in MLLMs
by: Wei, Hongchen, et al.
Published: (2025)

Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach
by: La Quang, Hai, et al.
Published: (2026)

Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification
by: Vu, Anh Mai, et al.
Published: (2025)

Perception-based Image Denoising via Generative Compression
by: Nguyen, Nam, et al.
Published: (2026)

EventBench: Towards Comprehensive Benchmarking of Event-based MLLMs
by: Liu, Shaoyu, et al.
Published: (2025)

MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
by: Zhang, Jiarui, et al.
Published: (2025)

PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation
by: Do, Khoi, et al.
Published: (2024)

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
by: Wang, Wei, et al.
Published: (2026)