| Hallucination is Inevitable: An Innate Limitation of Large Language Models Z Xu, S Jain, M Kankanhalli arXiv preprint arXiv:2401.11817, 2024 | 365 | 2024 |
| Embedding Symbolic Knowledge into Deep Networks Y Xie, Z Xu, MS Kankanhalli, KS Meel, H Soh Advances in Neural Information Processing Systems, 4233-4243, 2019 | 136 | 2019 |
| Learning Cross-scale Correspondence and Patch-based Synthesis for Reference-based Super-Resolution. H Zheng, M Ji, L Han, Z Xu, H Wang, Y Liu, L Fang BMVC 1, 2, 2017 | 73 | 2017 |
| Don’t Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation Z Xu, YS Rawat, Y Wong, MS Kankanhalli, M Shah Advances in Neural Information Processing Systems 35, 14890-14903, 2022 | 37 | 2022 |
| Relation-aware compositional zero-shot learning for attribute-object pair recognition Z Xu, G Wang, Y Wong, MS Kankanhalli IEEE Transactions on Multimedia 24, 3652-3664, 2021 | 29 | 2021 |
| Unsupervised motion representation learning with capsule autoencoders Z Xu, X Shen, Y Wong, MS Kankanhalli Advances in Neural Information Processing Systems 34, 3205-3217, 2021 | 22 | 2021 |
| Compute to Tell the Tale: Goal-Driven Narrative Generation Y Wong, S Fan, Y Guo, Z Xu, K Stephen, R Sheoran, A Bhamidipati, ... Proceedings of the 30th ACM International Conference on Multimedia, 6875-6882, 2022 | 15 | 2022 |
| GradMix: Multi-source transfer across domains and tasks J Li, Z Xu, W Yongkang, Q Zhao, M Kankanhalli Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2020 | 13 | 2020 |
| Semantic-Aware Triplet Loss for Image Classification G Wang, Y Guo, Z Xu, Y Wong, MS Kankanhalli IEEE Transactions on Multimedia 25, 4563-4572, 2022 | 8 | 2022 |
| Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness G Wang, Y Guo, Z Xu, M Kankanhalli Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 5 | 2024 |
| Cascaded image deblurring with combined image prior X Yuan, Z Xu, H Wang, Y Liu, L Fang 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP …, 2017 | 3 | 2017 |
| Utilizing high-level visual feature for indoor shopping mall localization Z Xu, H Zheng, M Pang, X Su, G Zhou, L Fang 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP …, 2017 | 2 | 2017 |
| A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023 Y Cheng, Z Xu, F Fang, D Lin, H Fan, Y Wong, Y Sun, M Kankanhalli arXiv preprint arXiv:2307.06569, 2023 | 1 | 2023 |
| Strong Preferences Affect the Robustness of Preference Models and Value Alignment Z Xu, M Kankanhalli The Thirteenth International Conference on Learning Representations, 2025 | | 2025 |
| Technical Report for ICML 2024 TiFA Workshop MLLM Attack Challenge: Suffix Injection and Projected Gradient Descent Can Easily Fool An MLLM Y Guo, Z Xu, X Xu, YK Wong, L Nie, M Kankanhalli arXiv preprint arXiv:2412.15614, 2024 | | 2024 |
| Bridging the Intent Gap: Knowledge-Enhanced Visual Generation Y Cheng, Z Xu, D Lin, H Cheng, Y Wong, Y Sun, JH Lim, M Kankanhalli arXiv preprint arXiv:2405.12538, 2024 | | 2024 |
| Appendix for Don’t Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation Z Xu, YS Rawat, Y Wong, MS Kankanhalli, M Shah | | |