Research & projects

Work shaped around
the hard part.

From long-horizon drift to low-step integration and irregular observations, each project starts with the system failure that matters.

2024 – Presentopen-source

GenODE / GICO

Learning context-conditioned integration clocks for frozen generative ODE and flow-matching backbones.

  • Efficient inference
  • Flow matching
2023 – Presentaccepted

Latent Laplace Diffusion

Parallel generative forecasting over irregular timestamps using stable latent trajectories.

  • Diffusion
  • Irregular time series
2026open-source

LoBiFlow

History-conditioned flow matching for generating level-2 limit order books.

  • Flow matching
  • Financial sequences
2024 – 2025published

TPE-AS

Adaptive Bayesian optimization for expensive, noisy portfolio-model tuning.

  • Bayesian optimization
  • Portfolio models
2023 – 2025published

C3E — GNN Capacity Estimation

Estimating hidden width and propagation depth from a channel-capacity view of graph representation learning.

  • Graph neural networks
  • Architecture search
2023 – 2024published

DGDNN

Decoupled graph diffusion for multi-stock movement prediction.

  • Graph diffusion
  • Financial ML
2023 – 2024published

MGDPR

Multi-relational graph diffusion with parallel retention for stock-trend classification.

  • Multi-relational graphs
  • Retention