Chirag Agarwal

Publication Activity (10 Years)

Years Active: 2015-2024
Publications (10 Years): 58

Top Topics

Trained Neural Networks

Top Venues

Medical Imaging: Image Processing

Publications

Sree Harsha Tanneru, Dan Ley, Chirag Agarwal, Himabindu Lakkaraju
On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models. CoRR (2024)
Chirag Agarwal, Sree Harsha Tanneru, Himabindu Lakkaraju
Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models. CoRR (2024)
Tessa Han, Aounon Kumar, Chirag Agarwal, Himabindu Lakkaraju
Towards Safe and Aligned Large Language Models for Medicine. CoRR (2024)
Sree Harsha Tanneru, Chirag Agarwal, Himabindu Lakkaraju
Quantifying Uncertainty in Natural Language Explanations of Large Language Models. AISTATS (2024)
Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju
Understanding the Effects of Iterative Prompting on Truthfulness. CoRR (2024)
Nicholas Kroeger, Dan Ley, Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju
Are Large Language Models Post Hoc Explainers? CoRR (2023)
Michael Llordes, Debasis Ganguly, Sumit Bhatia, Chirag Agarwal
Explain Like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation. SIGIR (2023)
Jiali Cheng, George Dasoulas, Huan He, Chirag Agarwal, Marinka Zitnik
GNNDelete: A General Strategy for Unlearning in Graph Neural Networks. CoRR (2023)
Shripad Vilasrao Deshmukh, Arpan Dasgupta, Balaji Krishnamurthy, Nan Jiang, Chirag Agarwal, Georgios Theocharous, Jayakumar Subramanian
Explaining RL Decisions with Trajectories. ICLR (2023)
Shripad Vilasrao Deshmukh, Arpan Dasgupta, Balaji Krishnamurthy, Nan Jiang, Chirag Agarwal, Georgios Theocharous, Jayakumar Subramanian
Explaining RL Decisions with Trajectories. CoRR (2023)
Ashish Seth, Mayur Hemani, Chirag Agarwal
DeAR: Debiasing Vision-Language Models with Additive Residuals. CVPR (2023)
Tarun Ram Menta, Surgan Jandial, Akash Patil, Vimal KB, Saketh Bachu, Balaji Krishnamurthy, Vineeth N. Balasubramanian, Chirag Agarwal, Mausoom Sarkar
Towards Estimating Transferability using Hard Subsets. CoRR (2023)
Shripad Vilasrao Deshmukh, Srivatsan R, Supriti Vijay, Jayakumar Subramanian, Chirag Agarwal
Counterfactual Explanation Policies in RL. CoRR (2023)
Sree Harsha Tanneru, Chirag Agarwal, Himabindu Lakkaraju
Quantifying Uncertainty in Natural Language Explanations of Large Language Models. CoRR (2023)
Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju
On the Trade-offs between Adversarial Robustness and Actionable Explanations. CoRR (2023)
Michael Llordes, Debasis Ganguly, Sumit Bhatia, Chirag Agarwal
Explain like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation. CoRR (2023)
Aounon Kumar, Chirag Agarwal, Suraj Srinivas, Soheil Feizi, Hima Lakkaraju
Certifying LLM Safety against Adversarial Prompting. CoRR (2023)
Ashish Seth, Mayur Hemani, Chirag Agarwal
DeAR: Debiasing Vision-Language Models with Additive Residuals. CoRR (2023)
Jiali Cheng, George Dasoulas, Huan He, Chirag Agarwal, Marinka Zitnik
GNNDelete: A General Strategy for Unlearning in Graph Neural Networks. ICLR (2023)
Chirag Agarwal, Marinka Zitnik, Himabindu Lakkaraju
Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods. AISTATS (2022)
Chirag Agarwal, Eshika Saxena, Satyapriya Krishna, Martin Pawelczyk, Nari Johnson, Isha Puri, Marinka Zitnik, Himabindu Lakkaraju
OpenXAI: Towards a Transparent Evaluation of Model Explanations. CoRR (2022)
Valentina Giunchiglia, Chirag Varun Shukla, Guadalupe Gonzalez, Chirag Agarwal
Towards Training GNNs using Explanation Directed Message Passing. CoRR (2022)
Valentina Giunchiglia, Chirag Varun Shukla, Guadalupe Gonzalez, Chirag Agarwal
Towards Training GNNs Using Explanation Directed Message Passing. LoG (2022)
Chirag Agarwal, Satyapriya Krishna, Eshika Saxena, Martin Pawelczyk, Nari Johnson, Isha Puri, Marinka Zitnik, Himabindu Lakkaraju
OpenXAI: Towards a Transparent Evaluation of Model Explanations. NeurIPS (2022)
Chirag Agarwal, Nari Johnson, Martin Pawelczyk, Satyapriya Krishna, Eshika Saxena, Marinka Zitnik, Himabindu Lakkaraju
Rethinking Stability for Attribution-based Explanations. CoRR (2022)
Chirag Agarwal, Daniel D'souza, Sara Hooker
Estimating Example Difficulty using Variance of Gradients. CVPR (2022)
Martin Pawelczyk, Chirag Agarwal, Shalmali Joshi, Sohini Upadhyay, Himabindu Lakkaraju
Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis. AISTATS (2022)
Chirag Agarwal, Owen Queen, Himabindu Lakkaraju, Marinka Zitnik
Evaluating Explainability for Graph Neural Networks. CoRR (2022)
Martin Pawelczyk, Shalmali Joshi, Chirag Agarwal, Sohini Upadhyay, Himabindu Lakkaraju
On the Connections between Counterfactual Explanations and Adversarial Examples. CoRR (2021)
Chirag Agarwal, Himabindu Lakkaraju, Marinka Zitnik
Towards a unified framework for fair and stable graph representation learning. UAI (2021)
Chirag Agarwal, Himabindu Lakkaraju, Marinka Zitnik
Towards a Unified Framework for Fair and Stable Graph Representation Learning. CoRR (2021)
Chirag Agarwal, Marinka Zitnik, Himabindu Lakkaraju
Towards a Rigorous Theoretical Analysis and Evaluation of GNN Explanations. CoRR (2021)
Chirag Agarwal, Shahin Khobahi, Dan Schonfeld, Mojtaba Soltanalian
CoroNet: a deep network architecture for enhanced identification of COVID-19 from chest x-ray images. Medical Imaging: Computer-Aided Diagnosis (2021)
Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Steven Wu, Himabindu Lakkaraju
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations. ICML (2021)
Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Zhiwei Steven Wu, Himabindu Lakkaraju
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations. CoRR (2021)
Daniel D'souza, Zach Nussbaum, Chirag Agarwal, Sara Hooker
A Tale Of Two Long Tails. CoRR (2021)
Chirag Agarwal, Sara Hooker
Estimating Example Difficulty using Variance of Gradients. CoRR (2020)
Naman Bansal, Chirag Agarwal, Anh Nguyen
SAM: The Sensitivity of Attribution Methods to Hyperparameters. CoRR (2020)
Naman Bansal, Chirag Agarwal, Anh Nguyen
SAM: The Sensitivity of Attribution Methods to Hyperparameters. CVPR (2020)
Chirag Agarwal, Anh Nguyen
Explaining Image Classifiers by Removing Input Features Using Generative Models. ACCV (6) (2020)
Chirag Agarwal, Shahin Khobahi, Arindam Bose, Mojtaba Soltanalian, Dan Schonfeld
Deep-URL: A Model-Aware Approach To Blind Deconvolution Based On Deep Unfolded Richardson-Lucy Network. CoRR (2020)
Naman Bansal, Chirag Agarwal, Anh Nguyen
SAM: The Sensitivity of Attribution Methods to Hyperparameters. CVPR Workshops (2020)
Chirag Agarwal, Peijie Chen, Anh Nguyen
Intriguing generalization and simplicity of adversarially trained neural networks. CoRR (2020)
Chirag Agarwal, Shahin Khobahi, Arindam Bose, Mojtaba Soltanalian, Dan Schonfeld
DEEP-URL: A Model-Aware Approach to Blind Deconvolution Based on Deep Unfolded Richardson-Lucy Network. ICIP (2020)
Chirag Agarwal, Dan Schonfeld, Anh Nguyen
Removing input features via a generative model to explain their attributions to classifier's decisions. CoRR (2019)
Chirag Agarwal, Anh Nguyen, Dan Schonfeld
Improving Robustness to Adversarial Examples by Encouraging Discriminative Features. ICIP (2019)
Mohammed Aloraini, Mehdi Sharifzadeh, Chirag Agarwal, Dan Schonfeld
Statistical Sequential Analysis for Object-based Video Forgery Detection. Media Watermarking, Security, and Forensics (2019)
Chirag Agarwal, Bo Dong, Dan Schonfeld, Anthony Hoogs
An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks. CoRR (2018)
Chirag Agarwal, Anh Nguyen, Dan Schonfeld
Improving Adversarial Robustness by Encouraging Discriminative Features. CoRR (2018)
Chirag Agarwal, Mehdi Sharifzadeh, Dan Schonfeld
CrossEncoders: A complex neural network compression framework. Visual Information Processing and Communication (2018)
Nivedita Khobragade, Chirag Agarwal
Multi-class segmentation of neuronal electron microscopy images using deep learning. Medical Imaging: Image Processing (2018)
Mehdi Sharifzadeh, Chirag Agarwal, Mahdi Salarian, Dan Schonfeld
A New Parallel Message-distribution Technique for Cost-based Steganography. CoRR (2017)
Mehdi Sharifzadeh, Chirag Agarwal, Mohammed Aloraini, Dan Schonfeld
Convolutional Neural Network Steganalysis's Application to Steganography. CoRR (2017)
Mehdi Sharifzadeh, Chirag Agarwal, Mohammed Aloraini, Dan Schonfeld
Convolutional neural network steganalysis's application to steganography. VCIP (2017)
Mohammad R. Arbabshirani, Ahmed H. Dallal, Chirag Agarwal, Aalpen Patel, Gregory Moore
Accurate segmentation of lung fields on chest radiographs using deep convolutional networks. Medical Imaging: Image Processing (2017)
Chirag Agarwal, Ahmed H. Dallal, Mohammad R. Arbabshirani, Aalpen Patel, Gregory Moore
Unsupervised quantification of abdominal fat from CT images using Greedy Snakes. Medical Imaging: Image Processing (2017)
Chirag Agarwal, Mehdi Sharifzadeh, Joe Klobusicky, Dan Schonfeld
CrossNets : A New Approach to Complex Learning. CoRR (2017)
Ahmed H. Dallal, Chirag Agarwal, Mohammad R. Arbabshirani, Aalpen Patel, Gregory Moore
Automatic estimation of heart boundaries and cardiothoracic ratio from chest x-ray images. Medical Imaging: Computer-Aided Diagnosis (2017)
Chirag Agarwal, Paul Hylander, Yogesh Mahajan, Jonathan Michelson, Vigyan Singhal
Compositional Reasoning Gotchas in Practice. FMCAD (2015)