Cover Image

Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sharma, Aditya, Saxon, Michael, Wang, William Yang
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models
by: Wang, Hengyi, et al.
Published: (2024)

Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)
by: Saxon, Michael, et al.
Published: (2024)

Document Haystack: A Long Context Multimodal Image/Document Understanding Vision LLM Benchmark
by: Huybrechts, Goeric, et al.
Published: (2025)

Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark
by: Wu, Tsung-Han, et al.
Published: (2024)

Can Vision Language Models Understand Mimed Actions?
by: Cho, Hyundong, et al.
Published: (2025)

Needle In A Multimodal Haystack
by: Wang, Weiyun, et al.
Published: (2024)

TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation
by: Feng, Weixi, et al.
Published: (2024)

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?
by: Zhao, Hongbo, et al.
Published: (2025)

Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
by: Zhang, Juntian, et al.
Published: (2025)

Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models
by: Zhou, Yucheng, et al.
Published: (2024)

Two Causally Related Needles in a Video Haystack
by: Li, Miaoyu, et al.
Published: (2025)

DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction
by: Tang, Hongyi, et al.
Published: (2026)

Lost in Translation? Translation Errors and Challenges for Fair Assessment of Text-to-Image Models on Multilingual Concepts
by: Saxon, Michael, et al.
Published: (2024)

How to Train Your Long-Context Visual Document Model
by: Veselka, Austin
Published: (2026)

LongVILA: Scaling Long-Context Visual Language Models for Long Videos
by: Chen, Yukang, et al.
Published: (2024)

Visual In-Context Learning for Large Vision-Language Models
by: Zhou, Yucheng, et al.
Published: (2024)

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
by: Xu, Haolei, et al.
Published: (2026)

Internalized Reasoning for Long-Context Visual Document Understanding
by: Veselka, Austin
Published: (2026)

GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts
by: Yuan, Fan, et al.
Published: (2025)

MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
by: Chowdhury, Sanjoy, et al.
Published: (2025)

VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context
by: Li, Yunxin, et al.
Published: (2024)

WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
by: Lu, Yujie, et al.
Published: (2024)

From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models
by: Bhatia, Mehar, et al.
Published: (2024)

GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models
by: Li, Mukai, et al.
Published: (2024)

Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
by: Tartaglini, Alexa R., et al.
Published: (2025)

Can Vision-Language Models Solve Visual Math Equations?
by: Choudhury, Monjoy Narayan, et al.
Published: (2025)

No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language Models
by: Sun, Min Woo, et al.
Published: (2025)

LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models
by: Tu, Shangqing, et al.
Published: (2025)

Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System
by: He, Lixuan, et al.
Published: (2025)

AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
by: Lin, Zichuan, et al.
Published: (2025)

MMLongCite: A Benchmark for Evaluating Fidelity of Long-Context Vision-Language Models
by: Zhou, Keyan, et al.
Published: (2025)

HAWAII: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language Models
by: Wang, Yimu, et al.
Published: (2025)

To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
by: Luo, Jiayun, et al.
Published: (2025)

Bootstrapping Action-Grounded Visual Dynamics in Unified Vision-Language Models
by: Qiu, Yifu, et al.
Published: (2025)

Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers
by: Wen, Yuxin, et al.
Published: (2024)

CAIRe: Cultural Attribution of Images by Retrieval-Augmented Evaluation
by: Yayavaram, Arnav, et al.
Published: (2025)

Advancing Multimodal In-Context Learning in Large Vision-Language Models with Task-aware Demonstrations
by: Li, Yanshu
Published: (2025)

DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models
by: Zou, Chengke, et al.
Published: (2024)

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
by: Wang, Zhaowei, et al.
Published: (2025)

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
by: Seo, Hoigi, et al.
Published: (2025)