Sahil Verma

25 papers A* 3A 1B 1Journal 17Unranked 3
YearRankTypeTitle / Venue / Authors
2025 A* conf
COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation.
CVPR
Arnav M. Das, Gantavya Bhatt, Lilly Kumari, Sahil Verma, Jeff A. Bilmes
2025 J jnl
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective.
Trans. Mach. Learn. Res.
Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P. Dickerson, Pin-Yu Chen, Jeff A. Bilmes
2025 J jnl
How Many Images Does It Take? Estimating Imitation Thresholds in Text-to-Image Models.
Trans. Mach. Learn. Res.
Sahil Verma, Royi Rassin, Arnav Mohanty Das, Gantavya Bhatt, Preethi Seshadri, Chirag Shah, Jeff A. Bilmes, Hannaneh Hajishirzi, Yanai Elazar
2025 A* conf
MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities.
EMNLP
Sahil Verma, Keegan Hines, Jeff A. Bilmes, Charlotte Siska, Luke Zettlemoyer, Hila Gonen, Chandan Singh
2025 J jnl
OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Modalities.
CoRR
Sahil Verma, Keegan Hines, Jeff A. Bilmes, Charlotte Siska, Luke Zettlemoyer, Hila Gonen, Chandan Singh
2024 J jnl
COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Learning.
CoRR
Arnav Mohanty Das, Gantavya Bhatt, Lilly Kumari, Sahil Verma, Jeff A. Bilmes
2024 J jnl
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review.
ACM Comput. Surv.
Sahil Verma, Varich Boonsanong, Minh Hoang, Keegan Hines, John Dickerson, Chirag Shah
2024 J jnl
How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold.
CoRR
Sahil Verma, Royi Rassin, Arnav Das, Gantavya Bhatt, Preethi Seshadri, Chirag Shah, Jeff A. Bilmes, Hannaneh Hajishirzi, Yanai Elazar
2023 J jnl
Effective Backdoor Mitigation Depends on the Pre-training Objective.
CoRR
Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P. Dickerson, Jeff A. Bilmes
2023 A conf
RecRec: Algorithmic Recourse for Recommender Systems.
CIKM
Sahil Verma, Ashudeep Singh, Varich Boonsanong, John P. Dickerson, Chirag Shah
2023 J jnl
RecRec: Algorithmic Recourse for Recommender Systems.
CoRR
Sahil Verma, Ashudeep Singh, Varich Boonsanong, John P. Dickerson, Chirag Shah
2022 A* conf
Amortized Generation of Sequential Algorithmic Recourses for Black-Box Models.
AAAI
Sahil Verma, Keegan Hines, John P. Dickerson
2021 J jnl
Amortized Generation of Sequential Counterfactual Explanations for Black-box Models.
CoRR
Sahil Verma, Keegan Hines, John P. Dickerson
2021 J jnl
Counterfactual Explanations for Machine Learning: Challenges Revisited.
CoRR
Sahil Verma, John P. Dickerson, Keegan Hines
2021 J jnl
Debug-localize-repair: a symbiotic construction for heap manipulations.
Formal Methods Syst. Des.
Sahil Verma, Subhajit Roy
2021 J jnl
Pitfalls of Explainable ML: An Industry Perspective.
CoRR
Sahil Verma, Aditya Lahiri, John P. Dickerson, Su-In Lee
2021 J jnl
Removing biased data to improve fairness and accuracy.
CoRR
Sahil Verma, Michael D. Ernst, René Just
2020 J jnl
Counterfactual Explanations for Machine Learning: A Review.
CoRR
Sahil Verma, John P. Dickerson, Keegan Hines
2020 J jnl
Debug-Localize-Repair: A Symbiotic Construction for Heap Manipulations.
CoRR
Sahil Verma, Subhajit Roy
2020 — conf
Facets of Fairness in Search and Recommendation.
BIAS
Sahil Verma, Ruoyuan Gao, Chirag Shah
2020 J jnl
Facets of Fairness in Search and Recommendation.
CoRR
Sahil Verma, Ruoyuan Gao, Chirag Shah
2020 J jnl
ShapeFlow: Dynamic Shape Interpreter for TensorFlow.
CoRR
Sahil Verma, Zhendong Su
2019 B conf
Benchmarking Symbolic Execution Using Constraint Problems - Initial Results.
ICTAI
Sahil Verma, Roland H. C. Yap
2018 — conf
Fairness definitions explained.
FairWare@ICSE
Sahil Verma, Julia Rubin
2017 — conf
Synergistic debug-repair of heap manipulations.
ESEC/SIGSOFT FSE
Sahil Verma, Subhajit Roy