Cover Image

Lost in Embeddings: Information Loss in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Wenyan, Tang, Raphael, Li, Chengzu, Zhang, Caiqi, Vulić, Ivan, Søgaard, Anders
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
by: Li, Chengzu, et al.
Published: (2024)

Visual Planning: Let's Think Only with Images
by: Xu, Yi, et al.
Published: (2025)

RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
by: Li, Jiaang, et al.
Published: (2025)

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
by: Li, Chengzu, et al.
Published: (2025)

Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
by: Li, Jiaang, et al.
Published: (2023)

Texture or Semantics? Vision-Language Models Get Lost in Font Recognition
by: Li, Zhecheng, et al.
Published: (2025)

11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis
by: Li, Chengzu, et al.
Published: (2025)

Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning
by: Li, Wenyan, et al.
Published: (2024)

Vision-Language Models under Cultural and Inclusive Considerations
by: Karamolegkou, Antonia, et al.
Published: (2024)

Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning
by: Li, Chengzu, et al.
Published: (2026)

Words Worth a Thousand Pictures: Measuring and Understanding Perceptual Variability in Text-to-Image Generation
by: Tang, Raphael, et al.
Published: (2024)

Dynamic Embedding of Hierarchical Visual Features for Efficient Vision-Language Fine-Tuning
by: Wei, Xinyu, et al.
Published: (2025)

Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation
by: Deng, Ken, et al.
Published: (2026)

MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
by: Zhang, Yin, et al.
Published: (2026)

Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models
by: Zhou, Ej, et al.
Published: (2025)

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
by: Wang, Weihang, et al.
Published: (2025)

Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings
by: Agrawal, Aakriti, et al.
Published: (2025)

Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning
by: Cambrin, Daniele Rege, et al.
Published: (2024)

Semantic Map-based Generation of Navigation Instructions
by: Li, Chengzu, et al.
Published: (2024)

MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models
by: Miao, Yongzhu, et al.
Published: (2023)

NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization
by: Zhang, Zheyuan, et al.
Published: (2025)

NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision
by: Li, Xiang, et al.
Published: (2024)

CLIP-Adapter: Better Vision-Language Models with Feature Adapters
by: Gao, Peng, et al.
Published: (2021)

ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models
by: Li, Bozhou, et al.
Published: (2025)

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
by: Kang, Jialiang, et al.
Published: (2025)

Vision-centric Token Compression in Large Language Model
by: Xing, Ling, et al.
Published: (2025)

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

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

EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models
by: Das, Rocktim Jyoti, et al.
Published: (2024)

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
by: Lu, Yifan, et al.
Published: (2025)

MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems
by: Zhu, Zifeng, et al.
Published: (2024)

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
by: Zhang, Huanyu, et al.
Published: (2025)

Vision-Language Models Do Not Understand Negation
by: Alhamoud, Kumail, et al.
Published: (2025)

VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information
by: Kamoi, Ryo, et al.
Published: (2024)

FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models
by: Cai, Hengxing, et al.
Published: (2025)

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
by: Jiang, Lei, et al.
Published: (2025)

FrEVL: Leveraging Frozen Pretrained Embeddings for Efficient Vision-Language Understanding
by: Bourigault, Emmanuelle, et al.
Published: (2025)

Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts
by: Chen, Qizhou, et al.
Published: (2024)

Vision Language Models Are Not (Yet) Spelling Correctors
by: Liang, Junhong, et al.
Published: (2025)

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
by: Tong, Jintao, et al.
Published: (2025)