Recursive Model

This is the PPT from the Weekly Lab Seminar at February 25, 2026.

Presenter: Taekhyun Park

This idea is currently being developed in a paper titled "LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models", which is under submission. You can get more detail at [here](https://thrillcrazyer.github.io/LoopUS)

(Park et al., 2026)



Enjoy Reading This Article?

Here are some more articles you might like to read next:

  • A Graph Representation Learning Approach for Imbalanced Ship Type Recognition Using AIS Trajectory Data
  • A Wiener Process Model with Dynamic Covariate for Degradation Modeling and Remaining Useful Life Prediction
  • Big-data-driven vessel destination prediction for smart port management
  • Queuing-Based Operational Indicators For Explaining and Predicting Port Operations
  • CT forecasting with Time-LLM