# Controlling Language and Diffusion Models by Transporting Activations

arXiv: https://arxiv.org/abs/2410.23054 · HTML: https://mlsanity.com/paper/2410.23054/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 51 of its 61 references that are in the map.
- First posted on arXiv 30 Oct 2024.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)

## Built on by (most cited first, 30 of 68)

- [A Unified Understanding and Evaluation of Steering Methods](https://mlsanity.com/paper/2502.02716/) (2025)
- [Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior](https://mlsanity.com/paper/2605.05115/) (2026)
- [ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment](https://mlsanity.com/paper/2602.17560/) (2026)
- [Observing and Controlling Features in Vision-Language-Action Models](https://mlsanity.com/paper/2603.05487/) (2026)
- [Activation Steering with a Feedback Controller](https://mlsanity.com/paper/2510.04309/) (2025)
- [LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss](https://mlsanity.com/paper/2503.10679/) (2025)
- [SAKE: Steering Activations for Knowledge Editing](https://mlsanity.com/paper/2503.01751/) (2025)
- [Video Unlearning via Low-Rank Refusal Vector](https://mlsanity.com/paper/2506.07891/) (2025)
- [Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models](https://mlsanity.com/paper/2502.15639/) (2025)
- [Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control](https://mlsanity.com/paper/2604.19018/) (2026)
- [SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models](https://mlsanity.com/paper/2510.26769/) (2025)
- [COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics](https://mlsanity.com/paper/2603.06495/) (2026)
- [Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations](https://mlsanity.com/paper/2501.19066/) (2025)
- [Sparse Autoencoders are Capable LLM Jailbreak Mitigators](https://mlsanity.com/paper/2602.12418/) (2026)
- [Concept Heterogeneity-aware Representation Steering](https://mlsanity.com/paper/2603.02237/) (2026)
- [Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention](https://mlsanity.com/paper/2605.05892/) (2026)
- [Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution](https://mlsanity.com/paper/2502.06809/) (2025)
- [DISCO: Disentangled Communication Steering for Large Language Models](https://mlsanity.com/paper/2509.16820/) (2025)
- [Steering at the Source: Style Modulation Heads for Robust Persona Control](https://mlsanity.com/paper/2603.13249/) (2026)
- [Evaluating Sparse Autoencoders for Monosemantic Representation](https://mlsanity.com/paper/2508.15094/) (2025)
- [Steering Large Reasoning Models towards Concise Reasoning via Flow Matching](https://mlsanity.com/paper/2602.05539/) (2026)
- [TADA! Tuning Audio Diffusion Models through Activation Steering](https://mlsanity.com/paper/2602.11910/) (2026)
- [Self-Improving Model Steering](https://mlsanity.com/paper/2507.08967/) (2025)
- [DSO: Direct Steering Optimization for Bias Mitigation](https://mlsanity.com/paper/2512.15926/) (2025)
- [Conditioned Activation Transport for T2I Safety Steering](https://mlsanity.com/paper/2603.03163/) (2026)
- [Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment](https://mlsanity.com/paper/2604.03867/) (2026)
- [CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification](https://mlsanity.com/paper/2604.14602/) (2026)
- [Don't Lose Focus: Activation Steering via Key-Orthogonal Projections](https://mlsanity.com/paper/2605.06342/) (2026)
- [Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control](https://mlsanity.com/paper/2606.04775/) (2026)
- [Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior](https://mlsanity.com/paper/2606.08454/) (2026)

## Abstract (arXiv)

The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control model generation by steering model activations in order to effectively induce or prevent the emergence of concepts or behaviors in the generated output. In this paper we introduce Activation Transport (AcT), a general framework to steer activations guided by optimal transport theory that generalizes many previous activation-steering works. AcT is modality-agnostic and provides fine-grained control over the model behavior with negligible computational overhead, while minimally impacting model abilities. We experimentally show the effectiveness and versatility of our approach by addressing key challenges in large language models (LLMs) and text-to-image diffusion models (T2Is). For LLMs, we show that AcT can effectively mitigate toxicity, induce arbitrary concepts, and increase their truthfulness. In T2Is, we show how AcT enables fine-grained style control and concept negation.