Hugging Face Trending Papers

Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy

Read the original on Hugging Face Trending Papers →

Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios. While positivity guarantees nonnegative reverse jump rates, it does not ensure Bayes realizability: ratios at a noisy state need not be jointly induced by any clean-token posterior under the forward kernel.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jul 28

UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective

arXiv:2607. 24507v1 Announce Type: cross Abstract: Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diffusion, where every token remains editable during sampling.

By Xiaoyi Jiang, Jingyuan Li, Yixuan Jiang, Wei Liu, Yi Zhu, Zuoqiang Shi, Pipi Hu
arXiv Machine Learning
Aug 4

Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs

arXiv:2608. 01023v1 Announce Type: new Abstract: We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and the provable per-input query cost of recovering the clean logits.

By Chi Wang, Hanwen Wang, Yu Xia, Zihan Wang, Guangdong Bai
arXiv AI
1d ago

SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation

arXiv:2608. 14647v1 Announce Type: cross Abstract: Dirty-history rollouts make multi-turn on-policy self-distillation (OPSD) brittle: once a student emits an erroneous intermediate reply, later turns are conditioned on that reply, and uniform distillation can spend loss on tokens that carry little corrective signal.

By Chenyang Jiang, Changhan Huang