Cover Image

The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ekin, Yigit, Gandelsman, Yossi
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Interpreting CLIP's Image Representation via Text-Based Decomposition
by: Gandelsman, Yossi, et al.
Published: (2023)

Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
by: Bu, Edmund, et al.
Published: (2025)

Learning Video Representations without Natural Videos
by: Yu, Xueyang, et al.
Published: (2024)

Interpreting the Second-Order Effects of Neurons in CLIP
by: Gandelsman, Yossi, et al.
Published: (2024)

Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising
by: Herbreteau, Sébastien, et al.
Published: (2022)

The More You See in 2D, the More You Perceive in 3D
by: Han, Xinyang, et al.
Published: (2024)

Vision Transformers Don't Need Trained Registers
by: Jiang, Nick, et al.
Published: (2025)

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
by: Jiang, Nick, et al.
Published: (2024)

Quantifying and Enabling the Interpretability of CLIP-like Models
by: Madasu, Avinash, et al.
Published: (2024)

The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement
by: Trivigno, Gabriele, et al.
Published: (2024)

CLIPAway: Harmonizing Focused Embeddings for Removing Objects via Diffusion Models
by: Ekin, Yigit, et al.
Published: (2024)

Teaching Humans Subtle Differences with DIFFusion
by: Chiquier, Mia, et al.
Published: (2025)

Steering CLIP's vision transformer with sparse autoencoders
by: Joseph, Sonia, et al.
Published: (2025)

Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
by: Li, Junxuan, et al.
Published: (2026)

An Empirical Study of Autoregressive Pre-training from Videos
by: Rajasegaran, Jathushan, et al.
Published: (2025)

Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs
by: Blasingame, Zander W., et al.
Published: (2024)

Jailbreaking Vision-Language Models Through the Visual Modality
by: Azulay, Aharon, et al.
Published: (2026)

LLMs can see and hear without any training
by: Ashutosh, Kumar, et al.
Published: (2025)

Synthesizing Moving People with 3D Control
by: Li, Boyi, et al.
Published: (2024)

AID: Attention Interpolation of Text-to-Image Diffusion
by: He, Qiyuan, et al.
Published: (2024)

Modular Energy Steering for Safe Text-to-Image Generation with Foundation Models
by: Tan, Yaoteng, et al.
Published: (2026)

Test-Time Training on Video Streams
by: Wang, Renhao, et al.
Published: (2023)

DECOR:Decomposition and Projection of Text Embeddings for Text-to-Image Customization
by: Jang, Geonhui, et al.
Published: (2024)

Steering Guidance for Personalized Text-to-Image Diffusion Models
by: Park, Sunghyun, et al.
Published: (2025)

CLIP Unreasonable Potential in Single-Shot Face Recognition
by: Luu, Nhan T.
Published: (2024)

FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition
by: Endo, Taichi, et al.
Published: (2026)

End-to-end Training for Text-to-Image Synthesis using Dual-Text Embeddings
by: Ahmed, Yeruru Asrar, et al.
Published: (2025)

CoRe: Context-Regularized Text Embedding Learning for Text-to-Image Personalization
by: Wu, Feize, et al.
Published: (2024)

Mitigating False Predictions In Unreasonable Body Regions
by: Ulrich, Constantin, et al.
Published: (2024)

SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
by: Zhang, Hongxiang, et al.
Published: (2024)

RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
by: Gokmen, Ahmet Berke, et al.
Published: (2025)

Interpreting the Weight Space of Customized Diffusion Models
by: Dravid, Amil, et al.
Published: (2024)

Addressing Text Embedding Leakage in Diffusion-based Image Editing
by: Mun, Sunung, et al.
Published: (2024)

RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation
by: Cao, Yuefan, et al.
Published: (2025)

ECNet: Effective Controllable Text-to-Image Diffusion Models
by: Li, Sicheng, et al.
Published: (2024)

SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editing
by: Dao, Thinh, et al.
Published: (2026)

Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings
by: Zarei, Arman, et al.
Published: (2024)

Uncovering the Text Embedding in Text-to-Image Diffusion Models
by: Yu, Hu, et al.
Published: (2024)

Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval
by: Jang, Young Kyun, et al.
Published: (2024)

Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization
by: Song, Yeji, et al.
Published: (2024)