NinaXander: Feasibility and Limits of Composing Frozen Language Models Across Architecture Families via a Shared Latent Space

The paper introduces NinaXander, a method for composing frozen language models from different architecture families by inserting a trained shared‑latent adapter between their layers. By running the initial layers of one model, converting the intermediate representation with the adapter, and then continuing with the remaining layers of another model, multiple composed models can be created without retraining. Experiments with RWKV and Pythia show that while some compositions preserve syntactic quality and reduce memory usage, none match the parent model’s accuracy and language‑modeling performance drops on out‑of‑domain data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• diffusion
• nlp