ECO: Evolving Core Knowledge for Efficient Transfer

Knowledge in modern neural networks is often entangled and structurally opaque, making current transfer methods--typically based on reusing entire parameter sets--inefficient and inflexible. Efforts to improve flexibility by reusing partial parameters frequently depend on handcrafted heuristics or rigid structural assumptions, which constrain generalization. In contrast, biological evolution enables efficient knowledge transfer by encoding only essential information into genes through iterative refinement under environmental pressure.