3 papers
cs.MM2026
Tri-Subspaces Disentanglement for Multimodal Sentiment Analysis
Chunlei Meng, Jiabin Luo, Zhenglin Yan +4
Multimodal Sentiment Analysis (MSA) integrates language, visual, and acoustic modalities to infer human sentiment. Most existing methods either focus on globally shared representat…
q-fin.ST2026
Beyond Visual Realism: Toward Reliable Financial Time Series Generation
Fan Zhang, Jiabin Luo, Zheng Zhang +3
Generative models for financial time series often create data that look realistic and even reproduce stylized facts such as fat tails or volatility clustering. However, these appar…
cs.CV2025
UniVid: The Open-Source Unified Video Model
Jiabin Luo, Junhui Lin, Zeyu Zhang +4
Unified video modeling that combines generation and understanding capabilities is increasingly important but faces two key challenges: maintaining semantic faithfulness during flow…