Imagen de Portada

Are MLMs Trapped in the Visual Room?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Yazhou, Zou, Chunwang, Liu, Qimeng, Rong, Lu, Yao, Ben, Lian, Zheng, Li, Qiuchi, Zhang, Peng, Qin, Jing
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories
por: Zhang, Yazhou, et al.
Publicado: (2025)

The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts
por: Zhang, Yuchen, et al.
Publicado: (2025)

LXLv2: Enhanced LiDAR Excluded Lean 3D Object Detection with Fusion of 4D Radar and Camera
por: Xiong, Weiyi, et al.
Publicado: (2025)

AirRoom: Objects Matter in Room Reidentification
por: Yao, Runmao, et al.
Publicado: (2025)

MAUP: Training-free Multi-center Adaptive Uncertainty-aware Prompting for Cross-domain Few-shot Medical Image Segmentation
por: Zhu, Yazhou, et al.
Publicado: (2025)

ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images
por: Jeong, Jinseo, et al.
Publicado: (2024)

AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding
por: Yao, Ruilin, et al.
Publicado: (2026)

Feature-Based Dual Visual Feature Extraction Model for Compound Multimodal Emotion Recognition
por: Liu, Ran, et al.
Publicado: (2025)

AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs
por: Chang, Boyu, et al.
Publicado: (2026)

Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis
por: Cai, Xinhao, et al.
Publicado: (2025)

Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation
por: Pei, Gensheng, et al.
Publicado: (2024)

VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection
por: Yao, Jianhang, et al.
Publicado: (2025)

Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
por: Zhang, Jianwei, et al.
Publicado: (2026)

PolyRoom: Room-aware Transformer for Floorplan Reconstruction
por: Liu, Yuzhou, et al.
Publicado: (2024)

A Light-weight Transformer-based Self-supervised Matching Network for Heterogeneous Images
por: Zhang, Wang, et al.
Publicado: (2024)

CAR: Controllable Autoregressive Modeling for Visual Generation
por: Yao, Ziyu, et al.
Publicado: (2024)

FAMNet: Frequency-aware Matching Network for Cross-domain Few-shot Medical Image Segmentation
por: Bo, Yuntian, et al.
Publicado: (2024)

MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning
por: Zhang, Qizhe, et al.
Publicado: (2023)

VisionTrap: Unanswerable Questions On Visual Data
por: Saadat, Asir, et al.
Publicado: (2025)

Is Sarcasm Detection A Step-by-Step Reasoning Process in Large Language Models?
por: Yao, Ben, et al.
Publicado: (2024)

Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?
por: Han, Cheng, et al.
Publicado: (2024)

SEP: Self-Enhanced Prompt Tuning for Visual-Language Model
por: Yao, Hantao, et al.
Publicado: (2024)

ViFP: A Framework for Visual False Positive Detection to Enhance Reasoning Reliability in VLMs
por: Zhang, Ben, et al.
Publicado: (2025)

TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability
por: Lian, Shiwei, et al.
Publicado: (2024)

Combating Noisy Labels through Fostering Self- and Neighbor-Consistency
por: Sun, Zeren, et al.
Publicado: (2026)

Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning
por: Zhang, Zhenyu, et al.
Publicado: (2026)

Evaluating Time Awareness and Cross-modal Active Perception of Large Models via 4D Escape Room Task
por: Dong, Yurui, et al.
Publicado: (2026)

COMOGen: A Controllable Text-to-3D Multi-object Generation Framework
por: Sun, Shaorong, et al.
Publicado: (2024)

Visual Room 2.0: Seeing is Not Understanding for MLLMs
por: Li, Haokun, et al.
Publicado: (2025)

Spatial-ORMLLM: Improve Spatial Relation Understanding in the Operating Room with Multimodal Large Language Model
por: He, Peiqi, et al.
Publicado: (2025)

FTMoMamba: Motion Generation with Frequency and Text State Space Models
por: Li, Chengjian, et al.
Publicado: (2024)

Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels
por: Zhao, Xin-yang, et al.
Publicado: (2025)

CauSight: Learning to Supersense for Visual Causal Discovery
por: Zhang, Yize, et al.
Publicado: (2025)

Training A Small Emotional Vision Language Model for Visual Art Comprehension
por: Zhang, Jing, et al.
Publicado: (2024)

Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
por: Zhang, Jing, et al.
Publicado: (2026)

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
por: Zou, Xin, et al.
Publicado: (2025)

SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding
por: Zhang, Yazhou, et al.
Publicado: (2024)

Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Prompting
por: Bo, Yuntian, et al.
Publicado: (2026)

VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Models
por: Zhao, Yi, et al.
Publicado: (2024)

Prim2Room: Layout-Controllable Room Mesh Generation from Primitives
por: Feng, Chengzeng, et al.
Publicado: (2024)