| Chart-to-text: A large-scale benchmark for chart summarization S Kantharaj, RTK Leong, X Lin, A Masry, M Thakkar, E Hoque, S Joty arXiv preprint arXiv:2203.06486, 2022 | 130 | 2022 |
| WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks? A Drouin, M Gasse, M Caccia, IH Laradji, M Del Verme, T Marty, ... arXiv preprint arXiv:2403.07718, 2024 | 31 | 2024 |
| Self-influence guided data reweighting for language model pre-training M Thakkar, T Bolukbasi, S Ganapathy, S Vashishth, S Chandar, ... arXiv preprint arXiv:2311.00913, 2023 | 16 | 2023 |
| HypMix: hyperbolic interpolative data augmentation R Sawhney, M Thakkar, S Agarwal, D Jin, D Yang, L Flek Proceedings of the 2021 conference on empirical methods in natural language …, 2021 | 14 | 2021 |
| Hyperbolic online time stream modeling R Sawhney, S Agarwal, M Thakkar, A Wadhwa, RR Shah Proceedings of the 44th International ACM SIGIR conference on research and …, 2021 | 13 | 2021 |
| Randomized smoothing with masked inference for adversarially robust text classifications HC Moon, S Joty, R Zhao, M Thakkar, X Chi arXiv preprint arXiv:2305.06522, 2023 | 11 | 2023 |
| Think: Temporal hypergraph hyperbolic network S Agarwal, R Sawhney, M Thakkar, P Nakov, J Han, T Derr 2022 IEEE International Conference on Data Mining (ICDM), 849-854, 2022 | 10 | 2022 |
| Sleepqa: A health coaching dataset on sleep for extractive question answering I Bojic, QC Ong, M Thakkar, E Kamran, IY Le Shua, JRE Pang, J Chen, ... Machine Learning for Health, 199-217, 2022 | 10 | 2022 |
| DMix: Adaptive distance-aware interpolative mixup R Sawhney, M Thakkar, S Pandit, R Soun, D Jin, D Yang, L Flek Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022 | 10 | 2022 |
| Chartgemma: Visual instruction-tuning for chart reasoning in the wild A Masry, M Thakkar, A Bajaj, A Kartha, E Hoque, S Joty arXiv preprint arXiv:2407.04172, 2024 | 5 | 2024 |
| Tweet based reach aware temporal attention network for NFT valuation R Sawhney, M Thakkar, R Soun, A Neerkaje, V Sharma, D Guhathakurta, ... Findings of the Association for Computational Linguistics: EMNLP 2022, 6321-6332, 2022 | 5 | 2022 |
| Workarena++: Towards compositional planning and reasoning-based common knowledge work tasks L Boisvert, M Thakkar, M Gasse, M Caccia, D Chezelles, T Le Sellier, ... arXiv preprint arXiv:2407.05291, 2024 | 3 | 2024 |
| Ciaug: Equipping interpolative augmentation with curriculum learning R Sawhney, R Soun, S Pandit, M Thakkar, S Malaviya, Y Pinter Proceedings of the 2022 Conference of the North American Chapter of the …, 2022 | 3 | 2022 |
| A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques M Thakkar, Q Fournier, MD Riemer, PY Chen, A Zouaq, P Das, S Chandar arXiv preprint arXiv:2406.04879, 2024 | 2 | 2024 |
| Learning Through Interpolative Augmentation of Dynamic Curvature Spaces P Chhabra, AT Neerkaje, S Agarwal, R Sawhney, M Thakkar, P Nakov, ... Proceedings of the 46th International ACM SIGIR Conference on Research and …, 2023 | 2 | 2023 |
| Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations L Liu, X Li, M Thakkar, X Li, S Joty, L Si, L Bing arXiv preprint arXiv:2211.08794, 2022 | 2 | 2022 |
| The browsergym ecosystem for web agent research D Chezelles, T Le Sellier, M Gasse, A Lacoste, A Drouin, M Caccia, ... arXiv preprint arXiv:2412.05467, 2024 | 1 | 2024 |
| Combining domain and alignment vectors to achieve better knowledge-safety trade-offs in llms M Thakkar, Y More, Q Fournier, M Riemer, PY Chen, A Zouaq, P Das, ... arXiv preprint arXiv:2411.06824, 2024 | 1 | 2024 |
| Randomized Smoothing with Masked Inference for Adversarially Robust NLP Systems HC Moon, S Joty, R Zhao, M Thakkar, X Chi | 1 | 2022 |
| Too Big to Fool: Resisting Deception in Language Models MR Samsami, ML Richter, J Rodriguez, M Thakkar, S Chandar, M Gasse arXiv preprint arXiv:2412.10558, 2024 | | 2024 |
Shafiq JotySenior Research Director at Salesforce Research, Assoc. Prof. at NTU (on leave)Verified email at ntu.edu.sg