Kushal Kafle

papers

690

total citations

papers (12)

Improving Visual Grounding by Encouraging Consistent Gradient-Based Explanations

CVPR 2023arXiv

citations

OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses

ECCV 2022arXiv

citations

FineMatch: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction

ECCV 2024arXiv

citations

FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication

CVPR 2024arXiv

citations

Improving Large Vision and Language Models by Learning from a Panel of Peers

ICCV 2025arXiv

citations

Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles

ICCV 2025arXiv

citations

AESOP: Abstract Encoding of Stories, Objects, and Pictures

ICCV 2021

citations

Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers

ECCV 2022

citations

Building Vision-Language Models on Solid Foundations with Masked Distillation

CVPR 2024

citations

Kushal Kafle

papers (12)

REMIND Your Neural Network to Prevent Catastrophic Forgetting

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

Learning To Predict Visual Attributes in the Wild

Improving Visual Grounding by Encouraging Consistent Gradient-Based Explanations

OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses

FineMatch: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction

FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication

Improving Large Vision and Language Models by Learning from a Panel of Peers

Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles

AESOP: Abstract Encoding of Stories, Objects, and Pictures

Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers

Building Vision-Language Models on Solid Foundations with Masked Distillation

papers (12)

REMIND Your Neural Network to Prevent Catastrophic Forgetting

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

Learning To Predict Visual Attributes in the Wild

Improving Visual Grounding by Encouraging Consistent Gradient-Based Explanations

OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses

FineMatch: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction

FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication

Improving Large Vision and Language Models by Learning from a Panel of Peers

Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles

AESOP: Abstract Encoding of Stories, Objects, and Pictures

Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers

Building Vision-Language Models on Solid Foundations with Masked Distillation