arXiv AI
CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Aug 31
CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models
Masked diffusion language models predict tokens from a partially observed response canvas, enabling bidirectional conditioning and parallel token refinement. Yet standard masked-diffusion decoders use...
arXiv AI
Aug 7
Answer First, Reason Later: Commitment Order in Diffusion LLMs
arXiv:2608. 05687v1 Announce Type: cross Abstract: Masked diffusion language models (dLLMs) can commit tokens in any order -- a freedom marketed as their core advantage over autoregressive decoding.
arXiv Computation and Language
Sep 1
ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding
arXiv:2608.29748v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive language model inference by having a lightweight draft model propose multiple candidate tokens, which a...
arXiv AI
4d ago
On Trajectory-Aware Training for Masked Diffusion Language Models
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...
arXiv AI
Aug 25
Length-Adaptive Decoding for Masked Diffusion Machine Translation
The paper introduces Entropy-Valley (EV), a training‑free method for selecting target length in masked diffusion machine translation. EV evaluates candidate canvases by mean predictive entropy from all‑mask forward passes, choosing the length the model is best prepared to fill. Compared to a baseline that uses training‑corpus length statistics, EV recovers a substantial portion of the COMET‑22 gain across En→Zh, Zh→En, and En→De, and expert evaluation confirms adequacy improvements, especially for Zh→En.
arXiv Machine Learning
Jun 11
Re-evaluating Confidence Remasking in Masked Diffusion Language Models
arXiv:2606. 12232v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel token generation.