Shivam Agarwal

I am a graduate student at University of Illinois at Urbana-Champaign (UIUC) where I study CS and AI. Previously, I was an Engineer at Cisco and a research intern at IIIT-Delhi and Vanderbilt University. I obtained my bachelors degree in ECE from Manipal Institute of Technology, India.

I am especially passionate about machine learning, natural language processing, and graph-based deep learning. I have been fortunate to contribute to a wide range of research directions, including large language models, text mining, text representation learning, spatio-temporal information processing, reinforcement learning, quantitative finance, and computational social sciences. I would be happy to discuss any project idea at the intersection of the above areas; feel free to reach out if you are interested!

Email  /  Google Scholar  /  LinkedIn  /  Github  /  Semantic Scholar

profile photo
Research

I'm interested in natural machine learning, and natural language processing. Recently, I have been working on making language AI more efficient and accessible. I am evaluating and improving large language models' reasoning capabilities, factuality, and trustworthiness.

acl23 Scaling Diffusion Language Models via Adaptation From Autoregressive Models

Shansan Gong*, Shivam Agarwal*, Yizhe Zhang, Jiacheng Ye, Lin Zheng, Mukai Li, Chenxin An, Peilin Zhao, Wei Bi, Jiawei Han, Hao Peng, Lingpeng Kong

acl23 Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy

SeongKu Kang, Shivam Agarwal, Bowen Jin, Dongha Lee, Hwanjo Yu, Jiawei Han
Proceedings of the ACM on Web Conference 2024 (WWW 2024)

acl23 DynaMiTE: Discovering Explosive Topic Evolutions with User Guidance

Nishant Balepur*, Shivam Agarwal*, Karthik Ramanan, Diyi Yang, Jiawei Han
Fingings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)

acl23 Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language Models

Pengcheng Jiang, Shivam Agarwal, Bowen Jin, Xuan Wang, Jiawei Han
Findings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)

sigir23 Learning Through Interpolative Augmentation of Dynamic Curvature Spaces

Parth Chhabra, Atula Tejaswi Neerkaje, Shivam Agarwal, Ramit Sawhney, Megh Thakkar, Preslav Nakov, Sudheer Chava
The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023)

icassp23 HyperSteg: Hyperbolic Learning For Deep Steganography

Shivam Agarwal, Ritesh Soun, Rahul Shivani, Vishnu Varanasi, Navroop Gill, Ramit Sawhney
2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023)

icdm22 THINK: Temporal Hypergraph Hyperbolic Network

Shivam Agarwal*, Ramit Sawhney*, Megh Thakkar, Preslav Nakov, Jiawei Han, Tyler Derr
IEEE International Conference on Data Mining (ICDM 2022)
[Slide]

naacl22 Cryptocurrency Bubble Detection: A New Stock Market Dataset, Financial Task & Hyperbolic Models

Ramit Sawhney*, Shivam Agarwal*, Vivek Mittal, Paolo Rosso, Vikram Nanda, Sudheer Chava
2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)
[Code]

sigir22 Towards suicide ideation detection through online conversational context

Ramit Sawhney*, Shivam Agarwal*, Atula Tejaswi Neerkaje, Nikolaos Aletras, Preslav Nakov, Lucie Flek
The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2022)
[Code]

acl22 HYPHEN: Hyperbolic Hawkes Attention For Text Streams

Shivam Agarwal, Ramit Sawhney, Sanchit Ahuja, Ritesh Soun, Sudheer Chava
60th Annual Meeting of the Association for Computational Linguistics (ACL 2022)
[Code]

aistats22 Orthogonal Multi-Manifold Enriching of Directed Networks

Ramit Sawhney*, Shivam Agarwal*, Atula Tejaswi, Kapil Pathak
The 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022)
[Code]

emnlp21 HypMix: Hyperbolic Interpolative Data Augmentation

Ramit Sawhney, Megh Thakkar, Shivam Agarwal, Di Jin, Diyi Yang, Lucie Flek
The 2021 Conference on Empirical Methods in Natural Language Processing (Proceedings of EMNLP 2021)
[Code]

uai21 Modeling Financial Uncertainty with Multivariate Temporal Entropy-based Curriculums

Ramit Sawhney, Arnav Wadhwa, Vivek Mittal, Ayush Mangal, Shivam Agarwal, Rajiv Shah
37th Conference on Uncertainty in Artificial Intelligence (UAI 2021)
[Code]

ijcai21 TEC: A Time Evolving Contextual Graph Model for Speaker State Analysis in Political Debates

Ramit Sawhney*, Shivam Agarwal*, Arnav Wadhwa, Rajiv Ratn Shah
30th International Joint Conference on Artificial Intelligence (IJCAI 2021), [AR=13.9%]
[Code]

sigir21 Hyperbolic Online Stream Modeling

Ramit Sawhney*, Shivam Agarwal*, Megh Thakkar, Arnav Wadhwa, Rajiv Ratn Shah
The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021)
[Code]

naacl21 Quantitative Day Trading From Natural Language Using Reinforcement Learning

Ramit Sawhney, Arnav Wadhwa, Shivam Agarwal, Rajiv Ratn Shah
2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics, (NAACL 2021)
[Code]

www21 Exploring the Scale-Free Nature of Stock Markets: Hyperbolic Graph Learning for Algorithmic Trading

Ramit Sawhney*, Shivam Agarwal*, Arnav Wadhwa, Rajiv Ratn Shah
30th The Web Conference, (WWW 2021)
[Code]

eacl21 FAST: Financial news and tweet based Time Aware network for Stock Trading

Ramit Sawhney, Arnav Wadhwa, Shivam Agarwal, Rajiv Ratn Shah
European Chapter of the Association for Computational Linguistics, (EACL 2021), [AR=24%]
[Code]

aaai21 Stock Selection via Spatiotemporal Hypergraph Attention Network: A Learning to Rank Approach

Ramit Sawhney*, Shivam Agarwal*, Arnav Wadhwa, Tyler Derr, Rajiv Ratn Shah
AAAI Conference on Artificial Intelligence, (AAAI 2021), [AR=21%]
[Code]

coling21 GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion

Ramit Sawhney, Arnav Wadhwa, Shivam Agarwal, Rajiv Ratn Shah
International Conference on Computational Linguistics, (COLING 2020), [AR=21%]
[Code]
(Outstanding Paper Award)

emnlp20 Deep Attentive Learning for Stock Movement Prediction From Social Media Text and Company Correlations

Ramit Sawhney*, Shivam Agarwal*, Arnav Wadhwa, Rajiv Ratn Shah
Empirical Methods in Natural Language Processing, (Proceedings of EMNLP 2020), [AR=24.6%]
[Code]

icdm20 Spatiotemporal Hypergraph Convolution Network for Stock Movement Forecasting

Ramit Sawhney, Shivam Agarwal, Arnav Wadhwa, Rajiv Ratn Shah
IEEE International Conference on Data Mining, (ICDM 2020), [AR=9.7%]
[Code]

Services
Program Committee Member, WWW, 2021
Reviewer for WSDM, EMNLP, ACL, AISTATS, CIKM, NAACL, ASONAM

* Indicates Joint First Authors