Our portfolio of research, competitions, and infrastructure work.
Research on hierarchical, verification-gated and recoverable workflows for scaling long-horizon AI-assisted research and agent execution.
Lead: Yuhe Sui
Authors: Jianing Zhang, Shufang Chen, Danlin Chen, Wang Zimeng, Xiaotong Li
Slicers: Yizhe Chia
Active research on faithful, auditable, trade-level FRTB attribution.
Geometric Attention Fine-Tuning: adapting the rule a pretrained Transformer uses to compare representations, not only the representations themselves.
Lead: Yuhe Sui
Research on attention geometry, representation-relative identifiability, and geometry-adaptive prediction.
Lead: Yuhe Sui
Authors: Jianing Zhang, Xiaotong Li
Research on softmax policy improvement, its robustness, and its failure modes.
Research on spectral-risk decisions, diverse scenarios, and selective robustness evaluation.
Theoretical research on softmax-attention approximation rank, support geometry, and robust interaction dimension.
An early-stage research programme with derived research in progress.
Lead: Yuhe Sui
An early-stage research programme with derived research in progress.
Lead: Yuhe Sui
A bilingual English/Chinese full-stack web application with a quantitative, multi-criteria scoring framework (mental load, physical load, difficulty) that ranks 100+ NTU student clubs and surfaces algorithmically-driven recommendations for students.
Participants: Yuhe Sui
A constrained Chinese financial-news overlay on classical risk-parity allocation, presented as a poster and oral at NLPCC 2026 Shared Task 4.
Participants: Yuhe Sui
2026 第五届中国未来金融分析师大赛
• Built a Greenwashing Risk Score across 1,676 Chinese green-bond issuances (2016–2025), using issue-spread regressions and portfolio sorts. • Pricing effects are weak unconditionally, but meaningful within credit-risk buckets after controls.
Participants: Yuhe Sui, Wang Zimeng, Luis Ji, Wang Zhoufu, Yu Jiaxue