Manning Gao

Manning Gao

Auto-generated profile, based on publicly available information

Manning Gao

South China Normal University, Guangzhou, China

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 November 2026
Verified
Conference Paper
Open access
MGManning Gao
Manning Gao
LZLeheng Zhang
Leheng Zhang
SHShiqin Han
Shiqin Han
HHHaifeng Hu
Haifeng Hu
YJYuncheng Jiang
Yuncheng Jiang
SMSijie Mai
Sijie Mai

14 September 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
LZLeheng Zhang
Leheng Zhang
MGManning Gao
Manning Gao
MJMenghua Jiang
Menghua Jiang
YLYuxia Lin
Yuxia Lin
HHHaifeng Hu
Haifeng Hu
SMSijie Mai
Sijie Mai
Multimodal sentiment analysis predicts continuous or ordinal affect from language, acoustic, and visual cues, but cross-modal alignment and per-stream reliability vary by sample. Previous fusion often collapses modalities into a symmetric or text-fixed representation, which may amplify inherent noise and ignore important information. Therefore, we propose PRISM, a primary-centric framework:(i) each modality is independently encoded by a parallel \emph{Variational Token Bottleneck} (\VTB) under a variational information-bottleneck objective, producing compact token-level latents together with token-level confidence estimates that quantify per-token reliability;(ii) a \emph{Differentiable Primary Router} (\DPR) then applies a Gumbel--Softmax relaxation to select a sample-dependent primary pathway from these bottleneck representations, rather than assuming a fixed dominant modality, and routes prediction exclusively through the enhanced primary stream instead of a pooled multimodal vector; and(iii) stacked InfoGate layers refine the selected primary by confidence-aware auxiliary-to-primary attention and adaptive auxiliary gating, using the \VTB confidence maps to downweight unreliable auxiliary tokens.We evaluate the model on both regression and classification datasets. While showing strong performance on regression tasks, the architecture also generalizes to binary humor and sarcasm classification.