# The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering arXiv: https://arxiv.org/abs/2603.17998 ยท HTML: https://mlsanity.com/paper/2603.17998/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. - Builds on 39 of its 44 references that are in the map. - First posted on arXiv 18 Mar 2026. ## Placed in - LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/) ## Builds on (most cited first, 30 of 39) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025) - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022) - [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022) - [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022) - [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023) - [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025) - [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025) - [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022) - [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022) - [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024) - [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022) - [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023) - [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023) - [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025) - [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024) - [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025) - [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023) - [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023) - [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024) - [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024) - [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025) - [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024) - [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023) - [Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models](https://mlsanity.com/paper/2311.12092/) (2023) - [LEDITS++: Limitless Image Editing using Text-to-Image Models](https://mlsanity.com/paper/2311.16711/) (2023) - [CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion](https://mlsanity.com/paper/2403.05121/) (2024) - [Goku: Flow Based Video Generative Foundation Models](https://mlsanity.com/paper/2502.04896/) (2025) ## Built on by (most cited first, 6 of 6) - [Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control](https://mlsanity.com/paper/2606.04775/) (2026) - [Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control](https://mlsanity.com/paper/2607.14943/) (2026) - [Token-to-Token Alignment of Text Embeddings for Semantic Blending](https://mlsanity.com/paper/2606.24021/) (2026) - [SemanticSlider3D: Training-Free Continuous Semantic Editing for 3D Objects](https://mlsanity.com/paper/2608.18560/) (2026) - [UniSlider: Perceptually Uniform Sliders for Continuous Image Editing](https://mlsanity.com/paper/2610.06831/) (2026) - [SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing](https://mlsanity.com/paper/2610.14253/) (2026) ## Abstract (arXiv) We present a training-free framework for continuous and controllable image editing at test time for text-conditioned generative models. In contrast to prior approaches that rely on additional training or manual user intervention, we find that a simple steering in the text-embedding space is sufficient to produce smooth edit control. Given a target concept (e.g., enhancing photorealism or changing facial expression), we use a large language model to automatically construct a small set of debiased contrastive prompt pairs, from which we compute a steering vector in the generator's text-encoder space. We then add this vector directly to the input prompt representation to control generation along the desired semantic axis. To obtain a continuous control, we propose an elastic range search procedure that automatically identifies an effective interval of steering magnitudes, avoiding both under-steering (no-edit) and over-steering (changing other attributes). Adding the scaled versions of the same vector within this interval yields smooth and continuous edits. Since our method modifies only textual representations, it naturally generalizes across text-conditioned modalities, including image and video generation. To quantify the steering continuity, we introduce a new evaluation metric that measures the uniformity of semantic change across edit strengths. We compare the continuous editing behavior across methods and find that, despite its simplicity and lightweight design, our approach is comparable to training-based alternatives, outperforming other training-free methods.