activity
20192022
most citedCan Adversarial Weight Perturbations Inject Neural Backdoors?

61 citations · 112 across the 7 of their papers we have counts for

collaborators

11 papers

cs.CL2022

Knowledge Transfer from Answer Ranking to Answer Generation

Matteo Gabburo, Rik Koncel-Kedziorski, Siddhant Garg +2

Recent studies show that Question Answering (QA) based on Answer Sentence Selection (AS2) can be improved by generating an improved answer from the top-k ranked answer sentences (t…

cs.CV2022

SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds

Siddhant Garg, Mudit Chaudhary

We present SeRP, a framework for Self-Supervised Learning of 3D point clouds. SeRP consists of encoder-decoder architecture that takes perturbed or corrupted point clouds as inputs…

cs.CV2022

Self-Labeling Refinement for Robust Representation Learning with Bootstrap Your Own Latent

Siddhant Garg, Dhruval Jain

In this work, we have worked towards two major goals. Firstly, we have investigated the importance of Batch Normalisation (BN) layers in a non-contrastive representation learning f…

cs.CL20211 cited

Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering

Siddhant Garg, Alessandro Moschitti

In this paper we propose a novel approach towards improving the efficiency of Question Answering (QA) systems by filtering out questions that will not be answered by them. This is…

cs.LG202061 cited

Can Adversarial Weight Perturbations Inject Neural Backdoors?

Siddhant Garg, Adarsh Kumar, Vibhor Goel +1

Adversarial machine learning has exposed several security hazards of neural models and has become an important research topic in recent times. Thus far, the concept of an "adversar…

cs.LG2020

Functional Regularization for Representation Learning: A Unified Theoretical Perspective

Siddhant Garg, Yingyu Liang

Unsupervised and self-supervised learning approaches have become a crucial tool to learn representations for downstream prediction tasks. While these approaches are widely used in…