Tuc Nguyen

According to our database, Tuc Nguyen authored at least 8 papers between 2024 and 2026.

Collaborative distances:

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

2026

Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence.

Tien-Phat Nguyen, Truong Nguyen, Minh-Phuc Truong, Tuc Nguyen, James Bailey, Trung Le

CoRR, May, 2026

ATLAS: Adaptive Test-Time Latent Steering with External Verifiers for Enhancing LLMs Reasoning.

Tuc Nguyen, Thai Le

CoRR, January, 2026

2025

ShareChat: A Dataset of Chatbot Conversations in the Wild.

Yueru Yan, Tuc Nguyen, Bo Su, Melissa Lieffers, Thai Le

CoRR, December, 2025

Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification.

Tuc Nguyen, Yifan Hu, Thai Le

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

NOMATTERXAI: Generating "No Matter What" Alterfactual Examples for Explaining Black-Box Text Classification Models.

Tuc Van Nguyen, James Michels, Hua Shen, Thai Le

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

Marrying Adapters and Mixup to Efficiently Enhance the Adversarial Robustness of Pre-Trained Language Models for Text Classification.

Tuc Nguyen, Thai Le

CoRR, 2024

Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers.

Tuc Nguyen, Thai Le

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning.

Tuc Nguyen, Thai Le

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024