Manh Nguyen

14 papers A* 2Journal 11Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention. CoRR Manh Nguyen, Anh Nguyen, Dung Nguyen, Svetha Venkatesh, Hung Le
2026	A*	`conf`	Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models. AAAI Manh Nguyen, Sunil Gupta, Hung Le
2025	J	`jnl`	CAAD: Context-Aware Adaptive Decoding for Truthful Text Generation. CoRR Manh Nguyen, Sunil Gupta, Hung Le
2025	J	`jnl`	Distance Is All You Need: Radial Dispersion for Uncertainty Estimation in Large Language Models. CoRR Manh Nguyen, Sunil Gupta, Hung Le
2025	J	`jnl`	GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation. CoRR Manh Nguyen, Sunil Gupta, Dai Do, Hung Le
2025	J	`jnl`	Graph Contrastive Learning via Spectral Graph Alignment. CoRR Manh Nguyen
2025	J	`jnl`	Nonnegative Matrix Factorization through Cone Collapse. CoRR Manh Nguyen, Daniel L. Pimentel-Alarcón
2025	J	`jnl`	Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models. CoRR Manh Nguyen, Sunil Gupta, Hung Le
2025	J	`jnl`	SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models. CoRR Dai Do, Manh Nguyen, Svetha Venkatesh, Hung Le
2025	J	`jnl`	Semi-Supervised Contrastive Learning with Orthonormal Prototypes. CoRR Huanran Li, Manh Nguyen, Daniel L. Pimentel-Alarcón
2025	J	`jnl`	Towards Robust Fact-Checking: A Multi-Agent System with Advanced Evidence Retrieval. CoRR Tam Trinh, Manh Nguyen, Truong-Son Hy
2025	J	`jnl`	Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models. CoRR Manh Nguyen, Dung Nguyen, Dai Do, Svetha Venkatesh, Hung Le
2024	A*	`conf`	Continual Relation Extraction via Sequential Multi-Task Learning. AAAI Thanh-Thien Le, Manh Nguyen, Tung Thanh Nguyen, Ngo Van Linh, Thien Huu Nguyen
2019	—	`conf`	Yours Truly? Survey on Accessibility of Our Personal Data in the Connected World. PerCom Workshops Manh Nguyen, Md. Osman Gani, Vaskar Raychoudhury

2023 — conf

Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

AISec

Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz

2026 — preprint

CCX: Enabling Unmodified Intel SGX Applications on Arm CCA.

arXiv

Matti Schulze, Thorsten Holz, Felix C. Freiling