activity
20212025
most citedAdaptive Second Order Coresets for Data-efficient Machine Learning

5 citations · 19 across the 14 of their papers we have counts for

collaborators

14 papers

cs.LG2025

Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity

Dang Nguyen, Ali Payani, Baharan Mirzasoleiman

Hallucination in large language models (LLMs) can be detected by assessing the uncertainty of model outputs, typically measured using entropy. Semantic entropy (SE) enhances tradit…

cs.AI2025

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap

Wenhan Yang, Spencer Stice, Ali Payani +1

Ensuring Vision-Language Models (VLMs) generate safe outputs is crucial for their reliable deployment. However, LVLMs suffer from drastic safety degradation compared to their LLM b…

cs.CV20243 cited

Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity

Siddharth Joshi, Arnav Jain, Ali Payani +1

Contrastive Language-Image Pre-training (CLIP) on large-scale image-caption datasets learns representations that can achieve remarkable zero-shot generalization. However, such mode…

cs.LG20243 cited

Investigating the Benefits of Projection Head for Representation Learning

Yihao Xue, Eric Gan, Jiayi Ni +2

An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection…

cs.LG20231 cited

Inference and Interference: The Role of Clipping, Pruning and Loss Landscapes in Differentially Private Stochastic Gradient Descent

Lauren Watson, Eric Gan, Mohan Dantam +2

Differentially private stochastic gradient descent (DP-SGD) is known to have poorer training and test performance on large neural networks, compared to ordinary stochastic gradient…

cs.CV2023

Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality

Xuxi Chen, Yu Yang, Zhangyang Wang +1

Dataset distillation aims to minimize the time and memory needed for training deep networks on large datasets, by creating a small set of synthetic images that has a similar genera…