Home/Publications

Publications

Filters:

Results for:

Multi-Reference Preference Optimization for Large Language Models

H. Le, Q. Tran, D. Nguyen, K. Do, S. Mittal, K. Ogueji, S. Venkatesh

2025 / pp. (accepted on Dec 10, 2024) / AAAI Conference on Artificial Intelligence (AAAI)

Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models

Q. Le, L. H. Dang, N. H. Le, T. Tran, T. M. Le

2025 / pp. (accepted on Dec 10, 2024) / AAAI Conference on Artificial Intelligence (AAAI)

Learning Structural Causal Models from Ordering: Identifiable Flow Models

M. K. Le, K. Do, T. Tran

2025 / pp. (accepted on Dec 10, 2024) / AAAI Conference on Artificial Intelligence (AAAI)

Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment

M. Hussonnois, T. G. Karimpanal, S. Rana

2025 / pp. (accepted on Dec 20, 2024) / International Conference on Autonomous Agents and Multiagent Systems (AAMAS)

Rapid Selection and Ordering of In-Context Demonstrations via Prompt Embedding Clustering

K. Pham, H. Le, M. Ngo, T. Tran

2025 / pp. (accepted on Jan 23, 2025) / International Conference on Learning Representations (ICLR)

Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning

H. Le, K. Do, D. Nguyen, S. Gupta, S. Venkatesh

2025 / pp. (accepted on Jan 23, 2025) / International Conference on Learning Representations (ICLR)

Causal Discovery via Bayesian Optimization

B. Duong, S. Gupta, T. Nguyen

2025 / pp. (accepted on Jan 23, 2025) / International Conference on Learning Representations (ICLR)

h-Edit: Effective and Flexible Diffusion-Based Editing via Doob’s h-Transform

T. Nguyen, K. Do, D. Kieu, T. Nguyen

2025 / pp. (accepted on Feb 27, 2025) / Conference on Computer Vision and Pattern Recognition (CVPR)

SimSMoE: Toward Efficient Training Mixture of Experts via Solving Representational Collapse

G. Do, H. Le, T. Tran

2025 / pp. (accepted on Jan 23, 2025) / Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)

ALPACA AGAINST VICUNA: Using LLMs to Uncover Memorization of LLMs

A. Kassem, O. Mahmoud, N. Mireshghallah, H. Kim, Y. Tsvetkov, Y. Choi, S. Saad, S. Rana

2025 / pp. (accepted on Jan 23, 2025) / Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)

Future Proofing Study: a cluster randomised controlled trial evaluating the effectiveness of a universal school-based cognitive-behavioural programme for adolescent depression

A. Werner-Seidler, A. Mackinnon, P. J. Batterham, A. L. Calear, M. Larsen, M. Torok, B. O'Dea, K. Maston, K. Huckvale, H. Fujimoto, L. Johnston, L. Brown, A. Batholomew, D. Bal, J. R. Beames, S. R. Skinner, K. M. Boydell, S. Schweizer, R. Lingam, Y. Perry, J. L. Hudson, J. Oei, K. Steinbeck, M. Teesson, S. Venkatesh, H. Christensen

2025 / Vol. 28, pp. e301426 / BMJ Mental Health