Meta AI’s LegoNN Builds Decoder Modules That Are Reusable Across Diverse Language Tasks Without Fine-Tuning | Synced

In the new paper LegoNN: Building Modular Encoder-Decoder Models, Meta AI researchers propose LegoNN, a procedure for building encoder-decoder architectures with decoder modules that can be shared ...

By · · 1 min read

Source: Synced | AI Technology & Industry Review

In the new paper LegoNN: Building Modular Encoder-Decoder Models, Meta AI researchers propose LegoNN, a procedure for building encoder-decoder architectures with decoder modules that can be shared across different tasks without finetuning or significant performance reductions.