Solving the Clive Wearing Problem: One-Shot Episodic Memory for Frozen Transformers

Tommi Niemi / Rotko Networks

Hidden-state episodic memory for frozen transformers. No gradients.
Teach via one forward pass, recall via cosine similarity + logit injection.
200-line Python reproduction included.

pip install transformers torch numpy && python python/epimem.py

README.md

@@ -0,0 +1,105 @@
+<br />
+<div align="center">
+
+  <h3 align="center">Solving the Clive Wearing Problem: One-Shot Episodic Memory for Frozen Transformers</h3>
+
+  <p align="center">
+    Gradient-free persistent learning through hidden-state episodic recall.
+    <br />
+    <a href="paper.md"><img src="https://img.shields.io/badge/Paper-Markdown-blue?style=flat-square" alt="Paper"></a>
+  </p>
+</div>
+
+---
+
+## Abstract
+
+Teach a frozen language model new facts **without gradient descent**. Store the model's own hidden states as episodic memories. On recall, inject stored representations as logit biases. One-shot. Persistent. No weight modification.
+
+## Key Result
+
+A frozen Qwen 2.5 0.5B taught three facts about a fictional entity:
+
+| Prompt | Taught | Recalled | Similarity |
+|--------|--------|----------|:---:|
+| "The capital of Zyphraxia is" | "Novaheim" | "Novaheim, a city of 100" | 1.000 |
+| "The ruler of Zyphraxia is" | "Queen Stellara" | "Queen Stellara. She is a beautiful woman" | 1.000 |
+| "The currency of Zyphraxia is" | "Glimmers" | "Glimmers. The currency is divided into" | 1.000 |
+
+**No gradients computed at any point.**
+
+## Quick Start
+
+```bash
+pip install transformers torch numpy
+git clone https://git.rotko.net/tommi/epimem
+cd epimem
+python python/epimem.py
+```
+
+This downloads Qwen 2.5 0.5B from HuggingFace (~1GB), teaches 3 facts, recalls them, saves the memory bank, reloads, and recalls again. Takes ~2 minutes on first run (model download), ~30 seconds after.
+
+### With ONNX (faster, no PyTorch)
+
+```bash
+pip install onnxruntime transformers numpy
+python export_onnx.py          # exports Qwen 2.5 as ONNX to models/
+python python/epimem.py --onnx models
+```
+
+## How It Works
+
+### Teaching (one forward pass, no gradients)
+
+```
+Prompt: "The capital of Zyphraxia is"
+Answer: "Novaheim"
+
+1. backbone("The capital of Zyphraxia is") → hidden state h (896-dim vector)
+2. backbone("The capital of Zyphraxia is Novaheim") → logit biases for "Novaheim"
+3. Store: (key=h, value=logit_biases) in memory bank
+```
+
+### Recall (similarity search + logit injection)
+
+```
+Query: "The capital of Zyphraxia is"
+
+1. backbone(query) → h_q (896-dim vector)
+2. cosine_sim(h_q, stored_key) = 1.000
+3. Inject: logits += stored_logit_biases (per-position)
+4. Generate: "Novaheim, a city of 100..."
+```
+
+### Why hidden states, not text (like RAG)
+
+RAG stores text, re-encodes it each time, consumes context window.
+We store the backbone's own internal representation — no re-encoding, no context consumption.
+
+## Files
+
+```
+python/epimem.py          ← standalone reproduction (~200 lines)
+export_onnx.py            ← ONNX export from HuggingFace
+paper.md                  ← full paper
+results/memory_bank.json  ← example: 896-dim hidden-state vectors
+schema/isis.fbs           ← FlatBuffer schema for memory bank
+schema/organism.fbs       ← FlatBuffer schema for organism state
+models/tokenizer/         ← Qwen 2.5 tokenizer files
+```
+
+## Citation
+
+```bibtex
+@article{niemi2026clivewearing,
+  title={Solving the Clive Wearing Problem: One-Shot Episodic Memory for Frozen Transformers},
+  author={Tommi Niemi},
+  year={2026},
+  organization={Rotko Networks},
+  url={https://git.rotko.net/tommi/epimem},
+}
+```
+
+## License
+
+MIT