Documents publiés en "2023"

Article de revue

Kazemnejad, A., Rezagholizadeh, M., Parthasarathi, P., & Anbil Parthipan, S. C. (2023). Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models. Findings of the Association for Computational Linguistics: EMNLP, 4305-4319. Lien externe

Madsen, A., Reddy, S., & Anbil Parthipan, S. C. (2023). Post-hoc Interpretability for Neural NLP: A Survey. ACM Computing Surveys, 55(8), 1-42. Lien externe

Vaibhav Mehta, S., Patil, D., Anbil Parthipan, S. C., & Strubell, E. (2023). An Empirical Investigation of the Role of Pre-training in Lifelong Learning. Journal of Machine Learning Research, 24, 50-50. Lien externe

Communication écrite

Nekoei, H., Badrinaaraayanan, A., Sinha, A., Amini, M., Rajendran, J., Mahajan, A., & Anbil Parthipan, S. C. (août 2023). Dealing with non-stationarity in decentralized cooperative multi-agent deep reinforcement learning via multi-timescale learning [Communication écrite]. 2nd Conference on Lifelong Learning Agents (CoLLAs 2023), Montreal, Qc. Canada. Non disponible

Nekoei, H., Zhao, X. T., Rajendran, J., Liu, M. A., & Anbil Parthipan, S. C. (août 2023). Towards few-shot coordination : revisiting ad-hoc teamplay challenge in the game of Hanabi [Communication écrite]. 2nd Conference on Lifelong Learning Agents (CoLLAs 2023), Montreal, Qc, Canada. Non disponible

Rahimi-Kalahroudi, A., Rajendran, J., Momennejad, I., van Seijen, H., & Anbil Parthipan, S. C. (août 2023). Replay buffer with local forgetting for adapting to local environment changes in deep model-based reinforcement learning [Communication écrite]. 2nd Conference on Lifelong Learning Agents (CoLLAs 2023), Montreal, Qc, Canada. Lien externe

Thakkar, M., Bolukbasi, T., Ganapathy, S., Vashishth, S., Anbil Parthipan, S. C., & Talukdar, P. (décembre 2023). Self-Influence Guided Data Reweighting for Language Model Pre-training [Communication écrite]. Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore. Lien externe

Zayed, A., Parthasarathi, P., Torcato Mordido, G. F., Palangi, H., Shabanian, S., & Anbil Parthipan, S. C. (février 2023). Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness [Communication écrite]. 37th AAAI Conference on Artificial Intelligence (AAAI 2023) and 35th Conference on Innovative Applications of Artificial Intelligence (IAAI 2023) and 13th Symposium on Educational Advances in Artificial Intelligence (EAAI 2023), Washington, DC, USA. Lien externe

Zhao, X., Pan, Y., Xiao, C., Anbil Parthipan, S. C., & Rajendran, J. (juillet 2023). Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning [Communication écrite]. 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023), Pittsburgh, PA, USA. Lien externe

Résumé

Prato, G., Huang, J., Parthasarathi, P., Sodhani, S., & Anbil Parthipan, S. C. (décembre 2023). EpiK-Eval: Evaluation for Language Models as Epistemic Models [Résumé]. Conference on Empirical Methods in Natural Language Processing, Singapore, Singapore. Lien externe