Reversible Diffusion Decoding for Diffusion Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912863728173056 |
|---|---|
| author | Wang, Xinyun Zhang, Min Cui, Sen Chen, Zhikang Jiang, Bo Kuang, Kun Lin, Mingbao |
| author_facet | Wang, Xinyun Zhang, Min Cui, Sen Chen, Zhikang Jiang, Bo Kuang, Kun Lin, Mingbao |
| contents | Diffusion language models enable parallel token generation through block-wise decoding, but their irreversible commitments can lead to stagnation, where the reverse diffusion process fails to make further progress under a suboptimal context.We propose Reversible Diffusion Decoding (RDD), a decoding framework that introduces reversibility into block-wise diffusion generation. RDD detects stagnation as a state-dependent failure of the reverse process and enables efficient backtracking to earlier blocks without recomputation via cached model states. To avoid repeated failure trajectories, RDD applies confidence-guided re-masking to selectively reinitialize uncertain tokens while preserving reliable context.This reversible formulation allows decoding to recover from early commitment errors while maintaining the parallel efficiency of diffusion-based generation. Experiments show that RDD improves generation robustness and quality over baselines with minimal computational overhead. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00150 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reversible Diffusion Decoding for Diffusion Language Models Wang, Xinyun Zhang, Min Cui, Sen Chen, Zhikang Jiang, Bo Kuang, Kun Lin, Mingbao Computation and Language Artificial Intelligence Diffusion language models enable parallel token generation through block-wise decoding, but their irreversible commitments can lead to stagnation, where the reverse diffusion process fails to make further progress under a suboptimal context.We propose Reversible Diffusion Decoding (RDD), a decoding framework that introduces reversibility into block-wise diffusion generation. RDD detects stagnation as a state-dependent failure of the reverse process and enables efficient backtracking to earlier blocks without recomputation via cached model states. To avoid repeated failure trajectories, RDD applies confidence-guided re-masking to selectively reinitialize uncertain tokens while preserving reliable context.This reversible formulation allows decoding to recover from early commitment errors while maintaining the parallel efficiency of diffusion-based generation. Experiments show that RDD improves generation robustness and quality over baselines with minimal computational overhead. |
| title | Reversible Diffusion Decoding for Diffusion Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.00150 |