mlsanityData to 7 Oct 2026

Embedding Inversion via Conditional Masked Diffusion Language Models

arXiv 2602.11047 ↗First posted 11 Feb 2026cs.CLcited by 0

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 10 of its 12 references that are in the map. First posted on arXiv 11 Feb 2026.

Builds on

10 of 12 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Simple and Effective Masked Diffusion Language Models11 Jun
  2. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct

Other references · 8

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2022Classifier-Free Diffusion Guidancecited by 5,717
  5. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  6. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  7. 2024jina-embeddings-v3: Multilingual Embeddings With Task LoRAcited by 138
  8. 2026Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddingscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Soft-Masked Diffusion Language Models
  2. 2026Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Models
  3. 2025Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
  4. 2026Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models
  5. 2026Auto-Regressive Masked Diffusion Models
  6. 2026Supportive Token Revealing for Fast Diffusion Language Model Decoding
  7. 2026Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models
  8. 2026Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching