22) "Exploring the limits of decoder-only models trained on public speech recognition corpora"
Ankit Gupta, George Saon, Brian Kingsbury
Annual Conference of the International Speech Communication Association (INTERSPEECH), 2024.
22) "Exploring the limits of decoder-only models trained on public speech recognition corpora"
Ankit Gupta, George Saon, Brian Kingsbury
Annual Conference of the International Speech Communication Association (INTERSPEECH), 2024.
21) "Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors"
Ido Amos, Jonathan Berant, Ankit Gupta
International Conference on Learning Representations (ICLR), 2024. (outstanding paper award)
20) "Simplifying and Understanding State Space Models with Diagonal Linear RNNs"
Ankit Gupta, Harsh Mehta, Jonathan Berant
arXiv preprint, 2022.
19) "Diagonal State Space Augmented Transformers for Speech Recognition"
George Saon, Ankit Gupta, Xiaodong Cui
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023.
18) "Analyzing Transformers in Embedding Space"
Guy Dar, Mor Geva, Ankit Gupta, Jonathan Berant
Annual Conference of the Association for Computational Linguistics (ACL), 2023.
BlackboxNLP @ EMNLP 2022. (non-archival version)
17) "Long Range Language Modeling via Gated State Spaces"
Harsh Mehta, Ankit Gupta, Ashok Cutkosky, Behnam Neyshabur
International Conference on Learning Representations (ICLR), 2023.
16) "On the Parameterization and Initialization of Diagonal State Space Models"
Albert Gu, Ankit Gupta, Karan Goel, Christopher Ré
Advances in Neural Information Processing Systems (NeurIPS), 2022.
15) "Diagonal State Spaces are as Effective as Structured State Spaces"
Ankit Gupta, Albert Gu, Jonathan Berant
Advances in Neural Information Processing Systems (NeurIPS), 2022. (spotlight talk)
14) "SCROLLS: Standardized CompaRison Over Long Language Sequences"
Uri Shaham, Elad Segal, Maor Ivgi, Avia Efrat, Ori Yoran, Adi Haviv, Ankit Gupta, Wenhan Xiong, Mor Geva, Jonathan Berant, Omer Levy
Empirical Methods in Natural Language Processing (EMNLP), 2022.
13) "Memory-efficient Transformers via Top-k Attention"
Ankit Gupta, Guy Dar, Shaya Goodman, David Ciprut, Jonathan Berant
Workshop on Simple and Efficient Natural Language Processing (SustaiNLP) @ EMNLP 2021.
12) "Value-aware Approximate Attention"
Ankit Gupta, Jonathan Berant
Empirical Methods in Natural Language Processing (EMNLP), 2021 (oral presentation)
11) "GMAT: Global Memory Augmentation for Transformers"
Ankit Gupta, Jonathan Berant
arXiv preprint, 2020.
10) "Injecting Numerical Reasoning Skills into Language Models"
Mor Geva*, Ankit Gupta* and Jonathan Berant
Annual Conference of the Association for Computational Linguistics (ACL), 2020.
9) "Break It Down: A Question Understanding Benchmark"
Tomer Wolfson, Mor Geva, Ankit Gupta, Matt Gardner, Yoav Goldberg, Daniel Deutch and Jonathan Berant
Transactions of the Association for Computational Linguistics (TACL), 2020.
8) "Unexpected Power of Low-Depth Arithmetic Circuits"
Ankit Gupta, Pritish Kamath, Neeraj Kayal and Ramprasad Saptharishi
Communications of the ACM, 60(6): 93-100 (2017).
7) "Arithmetic Circuits: Lower Bounds, Derandomization and Reconstruction"
Ankit Gupta
PhD Thesis. Chennai Mathematical Institute, 2015.
6) "Algebraic Geometric Techniques for Depth-4 PIT & Sylvester-Gallai Conjectures for Varieties"
Ankit Gupta
ECCC, 2014.
5) "Arithmetic circuits: A chasm at depth three"
Ankit Gupta, Pritish Kamath, Neeraj Kayal and Ramprasad Saptharishi
IEEE Symposium on Foundations of Computer Science (FOCS) 2013, pp. 578-587.
SIAM Journal on Computing, 45(3): 1064-1079 (2016) (special issue for FOCS)
invited to Communications of the ACM, Research Highlights.
4) "Approaching the chasm at depth four"
Ankit Gupta, Pritish Kamath, Neeraj Kayal and Ramprasad Saptharishi
IEEE Conference on Computational Complexity (CCC) 2013, pp. 65-73.
Journal of the ACM, 61(6): 33:1-33:16 (2014)
best paper award at CCC 2013.
3) "Random Arithmetic Formulas can be Reconstructed Efficiently"
Ankit Gupta, Neeraj Kayal and Youming Qiao
IEEE Conference on Computational Complexity (CCC) 2013, pp. 1-9.
Computational Complexity 23(2): 207-303 (2014) (special issue for CCC 2013)
2) "Reconstruction of Depth-4 Multilinear Circuits with Top Fan-in 2"
Ankit Gupta, Neeraj Kayal and Satya Lokam
ACM Symposium on Theory of Computing (STOC) 2012, pp. 625-642.
1) "Efficient Reconstruction of Random Multilinear Formulas"
Ankit Gupta, Neeraj Kayal and Satya Lokam
IEEE Symposium on Foundations of Computer Science (FOCS) 2011, pp. 778-787.