Ashwin Swaminathan

papers

348

total citations

papers (11)

THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models

CVPR 2024arXiv

citations

CPR: Retrieval Augmented Generation for Copyright Protection

CVPR 2024arXiv

citations

Diffusion Soup: Model Merging for Text-to-Image Diffusion Models

ECCV 2024arXiv

citations

A Meta-Learning Approach to Predicting Performance and Data Requirements

CVPR 2023arXiv

citations

Your representations are in the network: composable and parallel adaptation for large scale models

NEURIPS 2023arXiv

citations

Enhancing Numerical Prediction of MLLMs with Soft Labeling

ICCV 2025

citations

Scaling up Image Segmentation across Data and Tasks

CVPR 2025

citations

Ashwin Swaminathan

papers (11)

Multi-Modal Hallucination Control by Visual Information Grounding

On the Scalability of Diffusion-based Text-to-Image Generation

Learning Expressive Prompting With Residuals for Vision Transformers

SAFE: Machine Unlearning With Shard Graphs

THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models

CPR: Retrieval Augmented Generation for Copyright Protection

Diffusion Soup: Model Merging for Text-to-Image Diffusion Models

A Meta-Learning Approach to Predicting Performance and Data Requirements

Your representations are in the network: composable and parallel adaptation for large scale models

Enhancing Numerical Prediction of MLLMs with Soft Labeling

Scaling up Image Segmentation across Data and Tasks

papers (11)

Multi-Modal Hallucination Control by Visual Information Grounding

On the Scalability of Diffusion-based Text-to-Image Generation

Learning Expressive Prompting With Residuals for Vision Transformers

SAFE: Machine Unlearning With Shard Graphs

THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models

CPR: Retrieval Augmented Generation for Copyright Protection

Diffusion Soup: Model Merging for Text-to-Image Diffusion Models

A Meta-Learning Approach to Predicting Performance and Data Requirements

Your representations are in the network: composable and parallel adaptation for large scale models

Enhancing Numerical Prediction of MLLMs with Soft Labeling

Scaling up Image Segmentation across Data and Tasks