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

arXiv:2609.38261 · cs.CL, cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/Katagiri-Hoshino-Lab/NinaXander

Terminology

• Accuracy — 55× in this paper · explained in 1 episode
• Transformer — 39× in this paper · explained in 2 episodes
• KV cache — 24× in this paper · explained in 3 episodes
• Alignment — 22× in this paper · explained in 1 episode
• Latent Space — 12× in this paper · explained in 7 episodes
• Perplexity — 7× in this paper · explained in 3 episodes
• Frozen model — 6× in this paper · explained in 2 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Domain Shift — 3× in this paper · explained in 4 episodes
• Instruction Tuning — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Model Merging — 2× in this paper · explained in 2 episodes
• THE AFFINE CONTROL FOR ACCURACY EVALUATION — 2× in this paper
• Activation Function — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Convolutional Neural Networks (CNNs) — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Pseudo-labels — 1× in this paper · explained in 2 episodes
• Receptance Weighted Key Value — 1× in this paper
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models
• GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering