Cover Image

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Varma, Maya, Delbrouck, Jean-Benoit, Chen, Zhihong, Chaudhari, Akshay, Langlotz, Curtis
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
by: Varma, Maya, et al.
Published: (2025)

Learning Generalizable 3D Medical Image Representations from Mask-Guided Self-Supervision
by: Gao, Yunhe, et al.
Published: (2026)

Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models
by: Zhang, Yabin, et al.
Published: (2026)

LieRE: Lie Rotational Positional Encodings
by: Ostmeier, Sophie, et al.
Published: (2024)

A data- and compute-efficient chest X-ray foundation model beyond aggressive scaling
by: Wang, Chong, et al.
Published: (2026)

Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data
by: Moroianu, Stefania L., et al.
Published: (2025)

From Detection to Mitigation: Addressing Bias in Deep Learning Models for Chest X-Ray Diagnosis
by: Mottez, Clemence, et al.
Published: (2025)

Identifying Spurious Correlations using Counterfactual Alignment
by: Cohen, Joseph Paul, et al.
Published: (2023)

CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats
by: Chambon, Pierre, et al.
Published: (2024)

A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation
by: Chen, Zhihong, et al.
Published: (2024)

CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging
by: Kumar, Ashwin, et al.
Published: (2026)

CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback
by: Hein, Dennis, et al.
Published: (2024)

A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation
by: Zhang, Yabin, et al.
Published: (2026)

Toward expanding the scope of radiology report summarization to multiple anatomies and modalities
by: Chen, Zhihong, et al.
Published: (2022)

Focusing Image Generation to Mitigate Spurious Correlations
by: Li, Xuewei, et al.
Published: (2024)

Process Reward Models for Sentence-Level Verification of LVLM Radiology Reports
by: Thomas, Alois, et al.
Published: (2025)

MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders
by: Varma, Maya, et al.
Published: (2025)

ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning
by: Hao, Zhiwei, et al.
Published: (2024)

Unsupervised Concept Discovery Mitigates Spurious Correlations
by: Arefin, Md Rifat, et al.
Published: (2024)

UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning
by: Guan, Jiajin, et al.
Published: (2025)

Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset
by: Blankemeier, Louis, et al.
Published: (2024)

Let Samples Speak: Mitigating Spurious Correlation by Exploiting the Clusterness of Samples
by: Li, Weiwei, et al.
Published: (2025)

Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation
by: MaungMaung, AprilPyone, et al.
Published: (2024)

Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort
by: Kim, Jeeyung, et al.
Published: (2024)

Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
by: Noohdani, Fahimeh Hosseini, et al.
Published: (2024)

Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation
by: Zheng, Guangtao, et al.
Published: (2024)

CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest Radiography
by: Prakash, Eva, et al.
Published: (2026)

MERGETUNE: Continued Fine-Tuning of Vision-Language Models
by: Wang, Wenqing, et al.
Published: (2026)

Prompt Triage: Structured Optimization Enhances Vision-Language Model Performance on Medical Imaging Benchmarks
by: Singhvi, Arnav, et al.
Published: (2025)

PestVL-Net: Enabling Multimodal Pest Learning via Fine-grained Vision-Language Interaction
by: Li, Xueheng, et al.
Published: (2026)

Thermo-VL: Extending Vision-Language Models to Thermal Infrared Perception
by: Thushara, Rusiru, et al.
Published: (2026)

3VL: Using Trees to Improve Vision-Language Models' Interpretability
by: Yellinek, Nir, et al.
Published: (2023)

VL4Gaze: Unleashing Vision-Language Models for Gaze Following
by: Wang, Shijing, et al.
Published: (2025)

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
by: Liu, Chenruo, et al.
Published: (2025)

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
by: Zeng, Lunbin, et al.
Published: (2025)

Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?
by: Yang, Yiwei, et al.
Published: (2025)

Mitigating Spurious Correlations in Weakly Supervised Semantic Segmentation via Cross-architecture Consistency Regularization
by: Zhang, Zheyuan, et al.
Published: (2025)

Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations
by: Moll, Johannes, et al.
Published: (2025)

Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
by: Zhang, Jinrui, et al.
Published: (2024)

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
by: Elisha, Yehonatan, et al.
Published: (2026)