All items in the PolyU Institutional Research Archive (PIRA) are protected by copyright, with all rights reserved, unless otherwise indicated. No item in the PIRA may be reproduced for commercial or resale purpose.
Collection's Items (Sorted by Submit Date in Descending order): 1 to 20 of 3410
| Date | Title | Author(s) |
| 2026 | Semantic norms and structural relations in Chinese semantic composition : a dataset and analysis | Zhou, H; Chersoni, E ; Hsu, YY |
| 2026 | Prompting precision : guiding EAP students to narrow essay topics using GenAI | Cheng, MCM |
| 2026 | Central but decentered : repositioning the practitioner in design research involving practice | Luis Vega; Valle-Noronha, J; Vega, L |
| 2026 | Gated tree cross-attention for checkpoint-compatible syntax injection in decoder-only LLMs | Gao, X; Wang, S ; Ding, N |
| 2026 | Decoding the multimodal mind : generalizable brain-to-text translation via multimodal alignment and adaptive routing | Ye, C; Zhang, Y; Sun, J; Li, C; Zhao, Y; Wang, S |
| 2025 | Exploitation of flow-induced surface vibration for suppression of cavity noise | Leung, RCK ; Naseer, MR |
| 2025 | A comparative study of beamforming algorithms for
direction-of-arrival estimation of environmental noise sources | Rai, S ; Leung, RCK ; Leung, CWM |
| 2025 | Leveraging ordinal information for speech-based depression classification | Zuo, L ; Mak, MW |
| 2024 | Promoting independence of depression and speaker features for speaker disentanglement in speech-based depression detection | Zuo, L ; Mak, MW ; Tu, Y |
| 2025 | Disentangling speaker and content in pre-trained speech models with latent diffusion for robust speaker verification | Li, Z ; Mak, MW ; Chien, JT; Pilanci, M; Jin, Z ; Meng, H |
| 2025 | Grouped knowledge distillation with adaptive logit softening for speaker recognition | Gan, CX ; Tu, Y ; Jin, Z ; Mak, MW ; Lee, KA |
| 2025 | IDIR : identifying and distilling informative relations for speaker verification | Gan, CX ; Li, Z ; Jin, Z ; Huang, Z ; Mak, MW ; Lee, KA |
| 2024 | Asymmetric clean segments-guided self-supervised learning for robust speaker verification | Gan, CX ; Mak, MW ; Lin, W ; Chien, JT |
| 2025 | Bayesian learning for domain-invariant speaker verification and anti-spoofing | Li, J ; Mak, MW ; Rohdin, J; Lee, KA ; Hermansky, H |
| 2026 | Distilling attention knowledge for speaker verification | Jin, Z ; Liu, S; Li, Z; Gan, CX ; Huang, Z ; Mak, MW |
| 2025 | Denoising student features with diffusion models for knowledge distillation in speaker verification | Jin, Z ; Tu, Y ; Li, Z ; Huang, Z ; Gan, CX ; Mak, MW |
| 2026 | ChemPRM : improving retrosynthesis by structured intermediate process reward | Zhang, L ; Ye, X; Liu, L; Zhang, X; Fang, X; Rossi, L |
| 2026 | SuperCap : multi-resolution superpixel-based image captioning | Senior, H; Rossi, L ; Slabaugh, G; Yuan, S |
| 2026 | SP-GCRL : influence maximization on incomplete social graphs | Niu, H; Yang, Y; Zhang, L ; Li, H; Liang, J; Luo, Z; Rossi, L |
| 2026 | A digitized sustainable preservation framework for traditional garment-making techniques : a case study of Hong Kong cheongsam | Zhang, Q ; Ng, H |
Collection's Items (Sorted by Submit Date in Descending order): 1 to 20 of 3410
