activity
20172023
most citedHarnessing the Vulnerability of Latent Layers in Adversarially Trained Models

23 citations · 58 across the 35 of their papers we have counts for

collaborators
Showing 2021Show all

9 papers · 1 filter

cs.MA2021

Status-quo policy gradient in Multi-Agent Reinforcement Learning

Pinkesh Badjatiya, Mausoom Sarkar, Nikaash Puri +4

Individual rationality, which involves maximizing expected individual returns, does not always lead to high-utility individual or group outcomes in multi-agent problems. For instan…

cs.MA2021★ 1 cited

DeepABM: Scalable, efficient and differentiable agent-based simulations via graph neural networks

Ayush Chopra, Esma Gel, Jayakumar Subramanian +5

We introduce DeepABM, a framework for agent-based modeling that leverages geometric message passing of graph neural networks for simulating action and interactions over large agent…

cs.CL2021

MINIMAL: Mining Models for Data Free Universal Adversarial Triggers

Swapnil Parekh, Yaman Singla Kumar, Somesh Singh +3

It is well known that natural language models are vulnerable to adversarial attacks, which are mostly input-specific in nature. Recently, it has been shown that there also exist in…

cs.CV2021

ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priors

Ayush Chopra, Rishabh Jain, Mayur Hemani +1

Image-based virtual try-on involves synthesizing perceptually convincing images of a model wearing a particular garment and has garnered significant research interest due to its im…

cs.AI2021

Video2Skill: Adapting Events in Demonstration Videos to Skills in an Environment using Cyclic MDP Homomorphisms

Sumedh A Sontakke, Sumegh Roychowdhury, Mausoom Sarkar +3

Humans excel at learning long-horizon tasks from demonstrations augmented with textual commentary, as evidenced by the burgeoning popularity of tutorial videos online. Intuitively,…

eess.AS2021★ 10 cited

Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring

Yaman Kumar Singla, Avykat Gupta, Shaurya Bagga +3

Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable…