Cover Image

Losing the Plot: How VLM responses degrade on imperfect charts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shin, Philip Wootaek, Sampson, Jack, Narayanan, Vijaykrishnan, Marquez, Andres, Halappanavar, Mahantesh
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Disharmony: Forensics using Reverse Lighting Harmonization
by: Shin, Philip Wootaek, et al.
Published: (2025)

Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Models
by: Shin, Philip Wootaek, et al.
Published: (2024)

When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noise
by: Shin, Philip Wootaek, et al.
Published: (2026)

Towards High-Resolution Alignment and Super-Resolution of Multi-Sensor Satellite Imagery
by: Shin, Philip Wootaek, et al.
Published: (2025)

Parts-Mamba: Augmenting Joint Context with Part-Level Scanning for Occluded Human Skeleton
by: Shen, Tianyi, et al.
Published: (2025)

MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition
by: Zhao, Shu, et al.
Published: (2025)

KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep Hashing
by: Zhao, Shu, et al.
Published: (2024)

Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generation
by: Zhao, Shu, et al.
Published: (2025)

Face Time Traveller : Travel Through Ages Without Losing Identity
by: Kar, Purbayan, et al.
Published: (2026)

Smartphone-based Circular Plot Sampling for Forest Inventory
by: Sun, Su, et al.
Published: (2026)

REO-VLM: Transforming VLM to Meet Regression Challenges in Earth Observation
by: Xue, Xizhe, et al.
Published: (2024)

WISE-FUSE: Efficient Whole Slide Image Encoding via Coarse-to-Fine Patch Selection with VLM and LLM Knowledge Fusion
by: Shin, Yonghan, et al.
Published: (2025)

MGFFD-VLM: Multi-Granularity Prompt Learning for Face Forgery Detection with VLM
by: Chen, Tao, et al.
Published: (2025)

VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition
by: Zhang, Zaiwei, et al.
Published: (2024)

3D-Plotting Algorithm for Insects using YOLOv5
by: Mori, Daisuke, et al.
Published: (2024)

Enhancing End-to-End Autonomous Driving with Risk Semantic Distillaion from VLM
by: Qin, Jack, et al.
Published: (2025)

Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots
by: Wu, Chengyue, et al.
Published: (2024)

Impact of imperfect annotations on CNN training and performance for instance segmentation and classification in digital pathology
by: Jiménez, Laura Gálvez, et al.
Published: (2024)

Rethinking VLM Representation for VLA Initialization
by: Lin, Weifeng, et al.
Published: (2026)

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
by: Zhang, Di, et al.
Published: (2024)

Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM
by: Yang, Sihan, et al.
Published: (2025)

The Describe-Then-Generate Bottleneck: How VLM Descriptions Alter Image Generation Outcomes
by: Kodathala, Sai Varun, et al.
Published: (2025)

DocVLM: Make Your VLM an Efficient Reader
by: Nacson, Mor Shpigel, et al.
Published: (2024)

BERT-VQA: Visual Question Answering on Plots
by: Vu, Tai, et al.
Published: (2025)

InspectVLM: Unified in Theory, Unreliable in Practice
by: Wallace, Conor, et al.
Published: (2025)

Benchmarking and Enhancing VLM for Compressed Image Understanding
by: Zhang, Zifu, et al.
Published: (2025)

VLM Models and Automated Grading of Atopic Dermatitis
by: Lalonde, Marc, et al.
Published: (2025)

VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
by: Xu, Runsen, et al.
Published: (2024)

Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes
by: Chen, Jianqi, et al.
Published: (2024)

Self-Improving VLM Judges Without Human Annotations
by: Lin, Inna Wanyin, et al.
Published: (2025)

EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography
by: Li, Yuheng, et al.
Published: (2025)

Similarity-Aware Token Pruning: Your VLM but Faster
by: Jeddi, Ahmadreza, et al.
Published: (2025)

VICI: VLM-Instructed Cross-view Image-localisation
by: Zhang, Xiaohan, et al.
Published: (2025)

TRANSPORTER: Transferring Visual Semantics from VLM Manifolds
by: Stergiou, Alexandros
Published: (2025)

CPPO: Contrastive Perception Policy Optimization for VLM Agents
by: Rezaei, Ahmad, et al.
Published: (2026)

MyVLM: Personalizing VLMs for User-Specific Queries
by: Alaluf, Yuval, et al.
Published: (2024)

Physics-Guided VLM Priors for All-Cloud Removal
by: Xu, Liying, et al.
Published: (2026)

CogVLM: Visual Expert for Pretrained Language Models
by: Wang, Weihan, et al.
Published: (2023)

Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation
by: Kakda, Mohit, et al.
Published: (2026)

Plots Unlock Time-Series Understanding in Multimodal Models
by: Daswani, Mayank, et al.
Published: (2024)