# TimpaTeks: Automatic In-place Text Sequence Modification via Diffusion Language Model Steering

arXiv: https://arxiv.org/abs/2606.08408 · HTML: https://mlsanity.com/paper/2606.08408/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)
- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 7 of 7)

- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Controlling Language and Diffusion Models by Transporting Activations](https://mlsanity.com/paper/2410.23054/) (2024)
- [LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss](https://mlsanity.com/paper/2503.10679/) (2025)
- [Activation Steering for Masked Diffusion Language Models](https://mlsanity.com/paper/2512.24143/) (2025)

## Abstract (arXiv)

We extend activation steering to diffusion language models (DLMs) and study a novel problem that arose due to the inference mechanism of DLMs: Modifying a text in-place to manifest a different concept. We propose TimpaTeks, an automatic in-place text modification mechanism using DLMs. Experiments on IMDB movie reviews (sentiment) and a synthetic Cats and Dogs Dataset (arbitrary, more unconventional concept steering) show that TimpaTeks provides a feasible novel mechanism to steer diffusion language model outputs in-place. TimpaTeks enables in-place modification while simultaneously lowers sentence perplexity and retaining the original sentence structre without the need of instruction tuned models. TimpaTeks is also computationally cheaper than prompt-based DLM steering, as it performs denoising in-place rather than constructing an additional prompt-conditioned output sequence.