Cover Image

LLMs Can Compensate for Deficiencies in Visual Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Takishita, Sho, Gala, Jay, Mohamed, Abdelrahman, Inui, Kentaro, Kementchedjhieva, Yova
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Devil is in the EOS: Sequence Training for Detailed Image Captioning
by: Mohamed, Abdelrahman, et al.
Published: (2025)

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

SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation
by: Chen, Xiaofu, et al.
Published: (2025)

A Simple Data Augmentation Strategy for Text-in-Image Scientific VQA
by: Shoer, Belal, et al.
Published: (2025)

EFSA: Episodic Few-Shot Adaptation for Text-to-Image Retrieval
by: Huzaifa, Muhammad, et al.
Published: (2024)

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
by: Shahgir, Haz Sameen, et al.
Published: (2026)

Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs
by: Salazar, Israfel, et al.
Published: (2025)

LinguDistill: Recovering Linguistic Ability in Vision-Language Models via Selective Cross-Modal Distillation
by: Irawan, Patrick Amadeus, et al.
Published: (2026)

Analyzing Finetuning Representation Shift for Multimodal LLMs Steering
by: Khayatan, Pegah, et al.
Published: (2025)

Can VLMs Recall Factual Associations From Visual References?
by: Ashok, Dhananjay, et al.
Published: (2025)

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

VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?
by: Gado, Mohamed, et al.
Published: (2025)

Symbolic Grounding Reveals Representational Bottlenecks in Abstract Visual Reasoning
by: Vaishnav, Mohit, et al.
Published: (2026)

Give me a hint: Can LLMs take a hint to solve math problems?
by: Agrawal, Vansh, et al.
Published: (2024)

Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
by: Zhang, Jiarui, et al.
Published: (2024)

CHARTOM: A Visual Theory-of-Mind Benchmark for LLMs on Misleading Charts
by: Bharti, Shubham, et al.
Published: (2024)

Can Rule-Based Insights Enhance LLMs for Radiology Report Classification? Introducing the RadPrompt Methodology
by: Fytas, Panagiotis, et al.
Published: (2024)

Multimodal LLMs Struggle with Basic Visual Network Analysis: a VNA Benchmark
by: Williams, Evan M., et al.
Published: (2024)

Multimodal LLMs Can Reason about Aesthetics in Zero-Shot
by: Jiang, Ruixiang, et al.
Published: (2025)

Compensating Distribution Drifts in Class-incremental Learning of Pre-trained Vision Transformers
by: Rao, Xuan, et al.
Published: (2025)

LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP
by: Chen, Danlu, et al.
Published: (2024)

Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education
by: Wang, Junling, et al.
Published: (2026)

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
by: Zhou, Wenrui, 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)

Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space
by: Verma, Gaurav, et al.
Published: (2024)

LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation
by: Hashemi, Mohammad Abuzar, et al.
Published: (2021)

Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs
by: Wang, Wenxuan, et al.
Published: (2025)

Responses Fall Short of Understanding: Revealing the Gap between Internal Representations and Responses in Visual Document Understanding
by: Kawasaki, Haruka, et al.
Published: (2026)

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

How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding
by: Yu, Zhuoran, et al.
Published: (2025)

Multimodal Large Language Models to Support Real-World Fact-Checking
by: Geng, Jiahui, et al.
Published: (2024)

Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization
by: Lai, Zhengzhao, et al.
Published: (2025)

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning
by: Cocchi, Federico, et al.
Published: (2025)

Can Visual Encoder Learn to See Arrows?
by: Terashita, Naoyuki, et al.
Published: (2025)

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
by: Ahn, Jaewoo, et al.
Published: (2025)

LLMs Can Evolve Continually on Modality for X-Modal Reasoning
by: Yu, Jiazuo, et al.
Published: (2024)

LLMs can Compress LLMs: Adaptive Pruning by Agents
by: Kodathala, Sai Varun, et al.
Published: (2026)

MLLMs-Augmented Visual-Language Representation Learning
by: Liu, Yanqing, et al.
Published: (2023)

Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering
by: Cocchi, Federico, et al.
Published: (2024)

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
by: Han, Jiaming, et al.
Published: (2025)