Priyanshu Kumar

22 papers A* 1C 1Journal 11Unranked 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
Maximum sensitivity constrained active disturbance rejection control based on reduced-order observer for DC-DC boost converter.
Trans. Inst. Meas. Control
Priyanshu Kumar, Moina Ajmeri
2025 J jnl
A non-isolated buck-boost converter based on SEPIC topology for renewable energy applications.
Comput. Electr. Eng.
Priyanshu Kumar, Moina Ajmeri
2025 A* conf
Aligned LLMs Are Not Aligned Browser Agents.
ICLR
Priyanshu Kumar, Elaine Lau, Saranya Vijayakumar, Tu Trinh, Elaine T. Chang, Vaughn Robinson, Shuyan Zhou, Matt Fredrikson, Sean M. Hendryx, Summer Yue, Zifan Wang
2025 J jnl
DEEPAMBIGQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness.
CoRR
Jiabao Ji, Min Li, Priyanshu Kumar, Shiyu Chang, Saloni Potdar
2025 — conf
Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning.
EMNLP (Industry Track)
Yajie Li, Albert Galimov, Mitra Datta Ganapaneni, Pujitha Thejaswi, De Meng, Priyanshu Kumar, Saloni Potdar
2025 J jnl
Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning.
CoRR
Yajie Li, Albert Galimov, Mitra Datta Ganapaneni, Pujitha Thejaswi, De Meng, Priyanshu Kumar, Saloni Potdar
2025 J jnl
PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages.
CoRR
Priyanshu Kumar, Devansh Jain, Akhila Yerukola, Liwei Jiang, Himanshu Beniwal, Thomas Hartvigsen, Maarten Sap
2024 J jnl
PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models.
CoRR
Devansh Jain, Priyanshu Kumar, Samuel Gehman, Xuhui Zhou, Thomas Hartvigsen, Maarten Sap
2024 J jnl
Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents.
CoRR
Priyanshu Kumar, Elaine Lau, Saranya Vijayakumar, Tu Trinh, Scale Red Team, Elaine T. Chang, Vaughn Robinson, Sean Hendryx, Shuyan Zhou, Matt Fredrikson, Summer Yue, Zifan Wang
2023 — conf
Analysing Forecasting of Stock Prices: An Explainable AI Approach.
ICMLDE
Priyanshu Kumar, Lopamudra Hota, Vinay Anand Tikkiwal, Arun Kumar
2023 — conf
ODA_SRIB at SemEval-2023 Task 9: A Multimodal Approach for Improved Intimacy Analysis.
SemEval@ACL
Priyanshu Kumar, Amit Kumar, Jiban Prakash, Prabhat Lamba, Irfan Abdul
2023 — conf
The Use Of Deep Learning In Music Genre Classification.
ICCCNT
Priyanshu Kumar, Nancy Nancy, Amit Kumar, Harashleen Kour
2022 C conf
A Text Structural Analysis Model for Address Extraction.
NLDB
Rishabh Kumar, Kamal Jakhar, Hemant Tiwari, Naresh Purre, Priyanshu Kumar, Jiban Prakash, Vanraj Vala
2021 — conf
PAW at SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation : Exploring Cross Lingual Transfer, Augmentations and Adversarial Training.
SemEval@ACL/IJCNLP
Harsh Goyal, Aadarsh Singh, Priyanshu Kumar
2021 J jnl
Provably secure and biometric-based secure access of e-Governance services using mobile devices.
J. Inf. Secur. Appl.
Preeti Soni, Arup Kumar Pal, SK Hafizul Islam, Aadarsh Singh, Priyanshu Kumar
2021 — conf
SciDr at SDU-2020 : IDEAS - Identifying and Disambiguating Everyday Acronyms for Scientific Domain.
SDU@AAAI
Aadarsh Singh, Priyanshu Kumar
2021 J jnl
SciDr at SDU-2020: IDEAS - Identifying and Disambiguating Everyday Acronyms for Scientific Domain.
CoRR
Aadarsh Singh, Priyanshu Kumar
2020 — conf
An Explainable Machine Learning Approach for Definition Extraction.
MIND (2)
Priyanshu Kumar, Aadarsh Singh, Pramod Kumar, Chiranjeev Kumar
2020 — conf
DSC IIT-ISM at SemEval-2020 Task 6: Boosting BERT with Dependencies for Definition Extraction.
SemEval@COLING
Aadarsh Singh, Priyanshu Kumar, Aman Sinha
2020 J jnl
DSC IIT-ISM at SemEval-2020 Task 6: Boosting BERT with Dependencies for Definition Extraction.
CoRR
Aadarsh Singh, Priyanshu Kumar, Aman Sinha
2020 — conf
NutCracker at WNUT-2020 Task 2: Robustly Identifying Informative COVID-19 Tweets using Ensembling and Adversarial Training.
W-NUT@EMNLP
Priyanshu Kumar, Aadarsh Singh
2020 J jnl
NutCracker at WNUT-2020 Task 2: Robustly Identifying Informative COVID-19 Tweets using Ensembling and Adversarial Training.
CoRR
Priyanshu Kumar, Aadarsh Singh