Task-agnostic Continual Learning via Mixture of Sparse Experts (SETA) resolves multi-task negative transfer in plasma control by isolating task-specific tokamak disruption dynamics into separate sparse sub-networks while preserving shared transport representations, outperforming standard multi-task learning (MTL) and single-task learning (STL) on cross-campaign EAST datasets.
Adversarial Debate Score
50% survival rate under critique
Expert panel critique
Independent views, each critiquing the hypothesis on its own — the score rewards genuine disagreement and discounts consensus.
Related patents (prior art)
This hypothesis overlaps subject matter covered by existing third-party patents. It is published as research, not as a patentable claim of ours.
Supporting Research Papers
- Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Exist...
- Teacher-guided multi-task learning for integrated plasma monitoring on EAST
This paper integrates tokamak plasma disruption prediction, Edge-Localized Mode (ELM) monitoring, Multifaceted Asymmetric Radiation From the Edge (MARFE) detection, and H/L-mode identification into a ...
- Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability
Streaming Continual Learning (CL) typically converts a continuous stream into a sequence of discrete tasks through temporal partitioning. We argue that this temporal taskification step is not a neutra...
Formal Verification
Z3 checks whether the hypothesis is internally consistent, not whether it is empirically true.