Publications d'Jerry Huang

Jerry Huang

Domaines de recherche: Apprentissage profond, Traitement du langage naturel
(Passage Accéléré de la Maîtrise)

Activité

Mamba Modulation: On the Length Generalization of Mamba
Peng Lu*, Jerry Huang*, Qiuhao Zeng, Xinyu Wang, Boxing Wang, Philippe Langlais et Yufei Cui
Conference on Neural Information Processing Systems (NeurIPS), 2025.
#NLP, #RL
[arXiv]
Resona: Improving Context Copying in Linear Recurrence Models with Retrieval
Jerry Huang*, Linrui Ma*, Xinyu Wang*, Peng Lu, Prasanna Parthasarathi, Xiao-Wen Chang, Boxing Chen et Yufei Cui
Conference on Language Modeling (COLM), 2025.
#NLP, #DL
[openreview], [arXiv]
Manifold Metric: A Loss Landscape Approach for Predicting Model Performance
Pranshu Malviya, Jerry Huang, Ariside Baratin, Quentin Fournier et Sarath Chandar
Conference on Lifelong Learning Agents (CoLLAs), 2025.
#DL
[arXiv]
Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Boxing Chen et Sarath Chandar
Findings of the Association for Computational Linguistics (ACL), 2025.
#NLP
[acl], [arXiv]
Calibrated Language Models and How to Find Them with Label Smoothing
Jerry Huang*, Peng Lu* et Qiuhao Zeng
International Conference on Machine Learning, 2025.
#NLP
[openreview], [arXiv]

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models
Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh et Sarath Chandar
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.
#NLP
[acl], [arXiv]
Do Large Language Models Know How Much They Know?
Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani et Sarath Chandar
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.
#NLP
[acl], [arXiv]
Promoting Exploration in Memory-Augmented Adam using Critical Momenta
Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu et Sarath Chandar
Transactions on Machine Learning Research (TMLR), 2024.
#DL
[openreview], [arXiv]

EpiK-Eval: Evaluation for Language Models as Epistemic Models
Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani et Sarath Chandar
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
#NLP
[acl], [openreview], [arXiv], [code]