DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to add a test-time training memory to a model with Robo TTT

Wrap attended action chunks with TTTWrapper and an MLP memory in a few lines of PyTorch.

Who it is forA robotics researcher who wants to try RoboTTT ideas in an existing policy.

The problemReimplementing a new paper's method from scratch is slow.

The outcomeA working TTT layer returning outputs and next fast weights with matching shapes.

What you need first

  • Python with PyTorch

Steps

  1. Install with pip install robo-ttt
  2. Build a 2-layer MLP memory and wrap it in MemoryKeyValueBind
  3. Create TTTWrapper(512, memory = memory)
  4. Pass action chunks and check the output shape

Prompt for your agent

Install lucidrains/robo_ttt, run the basic MemoryKeyValueBind plus TTTWrapper example on random tensors of shape (2, 5, 4, 512), and confirm the output shape matches the input.

Caveat. It is an unofficial implementation of the paper, so verify results against the original work.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for lucidrains/robo_ttt and "Add a test-time training memory to a model"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer