Findings of ACL 2023
29 citations
Joseph R., Liu T., Ng A.B., See S., Rai S.
A hand-annotated news headline dataset supports evaluation of how language models interpret and generate metaphors.
ACL 2022
25 citations
Liu T. and Soh D.
Two measures describe changes in word order and vocabulary, helping researchers inspect paraphrase datasets and select generated paraphrases.
IEEE Access 2025
13 citations
Huangsuwan K., Liu T., See S., Ng A.B., Vateekul P.
Diffusion-generated images train an additional model to help federated learning cope with differences in data across participating sites.
ACL-IJCNLP 2021
7 citations
Best Demonstration Runner-up Award
Hongwimol P., Kehasukcharoen P., Laohawarutchai P., Lertvittayakumjorn P., Ng A.B., Lai Z., Liu T., Vateekul P.
A literature search tool uses a knowledge graph to explain returned papers and show connections between research topics.
arXiv 2026
2 citations
Arefeen R., Miao X., Tong R., Ng A.B., See S., Liu T.
arXiv 2026
1 citation
Anand A., Ramesh M., Mittal A., Kumar A., Vyalla R.R., Cambria E., Wang Z., Liu T., Ng A.B., See S., Shah R.R.
A structured survey maps LLM reasoning paradigms, methods, and failure modes across more than 300 recent papers.
ACM MM Workshop 2025
1 citation
Rajendran M., Tan D., Liu T., Ng A.B., Lee J.S., Wei E.Y., See S.
A modular panel of AI personas combines knowledge-grounded responses with synthetic data to make digital advisors more consistent, personalised, and inclusive.
arXiv 2026
1 citation
Kukreja D., Prasad K., Anand A., Wang Z., Cambria E., Liu T., Ng A.B., See S., Chatterjee B.
FORGE updates model weights as gradients are computed instead of storing them, cutting optimizer memory by more than half and speeding small-batch LLM training.
IEEE SOLI 2025
0 citations
Best Paper Award
Chan J.Y., Guo H., Liu T., Ng A.B., See S.
A survey compares how data-poisoning attacks affect statistical models, conventional deep learning, and foundation models, helping practitioners weigh robustness against performance.
IEEE ISBI 2026
0 citations
Gopikrishna G., Panicke M.R., Liu T., Ng A.B., See S.
A deep learning multibeamformer uses tunable weight fusion and patch-wise learning for efficient, depth-independent ultrasound reconstruction.
