Embedding Inversion via Conditional Masked Diffusion Language Models
We frame embedding inversion as conditional masked diffusion, recovering all tokens in parallel through iterative denoising rather than sequential autoregressive generation. A masked diffusion language model is conditioned on the target embedding via adaptive layer normalization, requiring only 8 forward passes with no access to the target encoder at inference time. On 32-token sequences across three embedding models, the method achieves token recovery through parallel denoising without requiring encoder access, iterative correction, or architecture-specific alignment. Source code and live demo are available at https://github.com/jina-ai/embedding-inversion-demo.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models
Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing. We introduce DICE (Discrete Inversion for Controllable Editi…
Image GenerationLanguage ModelingLanguage ModellingMasked Language ModelingNull-text Inversion for Editing Real Images using Guided Diffusion Models
Recent text-guided diffusion models provide powerful image generation capabilities. Currently, a massive effort is given to enable the modification of these images using text only as means to offer intuitive and versatil…
Image GenerationText-based Image EditingDiffUMI: Training-Free Universal Model Inversion via Unconditional Diffusion for Face Recognition
Face recognition technology presents serious privacy risks due to its reliance on sensitive and immutable biometric data. To address these concerns, such systems typically convert raw facial images into embeddings, which…
Face GenerationFace RecognitionImage GenerationPrivacy Preserving+1Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models
Recently large-scale language-image models (e.g., text-guided diffusion models) have considerably improved the image generation capabilities to generate photorealistic images in various domains. Based on this success, cu…
Image GenerationMachine Unlearning for Masked Diffusion Language Models
Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models. Unlike autoregressive models, which generate text sequentially, MDLM…