Lucio M. Dery

According to our database, Lucio M. Dery authored at least 15 papers between 2018 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Context Training with Active Information Seeking.

Zeyu Huang, Adhiguna Kuncoro, Qixuan Feng, Jiajun Shen, Lucio M. Dery, Arthur Szlam, Marc'Aurelio Ranzato

CoRR, May, 2026

Latent Space Communication via K-V Cache Alignment.

Lucio M. Dery, Zohar Yahav, Henry Prior, Qixuan Feng, Jiajun Shen, Arthur Szlam

CoRR, January, 2026

2025

Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo.

Zachary Charles, Gabriel Teston, Lucio M. Dery, John Keith Rush, Nova Fallen, Zachary Garrett, Arthur D. Szlam, Arthur Douillard

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

2024

On Resource Efficient Transfer Learning via End Task Aware Training

Lucio M. Dery

PhD thesis, 2024

Multitask Learning Can Improve Worst-Group Outcomes.

Atharva Kulkarni, Lucio M. Dery, Amrith Setlur, Aditi Raghunathan, Ameet Talwalkar, Graham Neubig

Trans. Mach. Learn. Res., 2024

Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes.

Lucio M. Dery, Steven Kolawole, Jean-François Kagey, Virginia Smith, Graham Neubig, Ameet Talwalkar

CoRR, 2024

DeMuX: Data-efficient Multilingual Learning.

Simran Khanuja, Srinivas Gowriraj, Lucio M. Dery, Graham Neubig

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

2023

Transfer Learning for Structured Pruning under Limited Task Data.

Lucio M. Dery, David Grangier, Awni Hannun

CoRR, 2023

Cross-Modal Fine-Tuning: Align then Refine.

Junhong Shen, Liam Li, Lucio M. Dery, Corey Staten, Mikhail Khodak, Graham Neubig, Ameet Talwalkar

Proceedings of the International Conference on Machine Learning, 2023

AANG : Automating Auxiliary Learning.

Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Multi-step Planning for Automated Hyperparameter Optimization with OptFormer.

Lucio M. Dery, Abram L. Friesen, Nando de Freitas, Marc'Aurelio Ranzato, Yutian Chen

CoRR, 2022

Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative.

Lucio M. Dery, Paul Michel, Ameet Talwalkar, Graham Neubig

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Auxiliary Task Update Decomposition: the Good, the Bad and the neutral.

Lucio M. Dery, Yann N. Dauphin, David Grangier

Proceedings of the 9th International Conference on Learning Representations, 2021

2018

Audio to Body Dynamics.

Eli Shlizerman, Lucio M. Dery, Hayden Schoen, Ira Kemelmacher-Shlizerman

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos.

De-An Huang, Shyamal Buch, Lucio M. Dery, Animesh Garg, Li Fei-Fei, Juan Carlos Niebles

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018