Limits of Confidence in Diffusion
TL;DR · AI 摘要
Limits of Confidence in Diffusion - Apple Machine Learning Research research area Methods and Algorithms content type pa...
核心要点
- 主题聚焦：Limits of Confidence in Diffusion
- 来源：Apple Machine Learning Research，建议结合原文判断细节。
- AI 分析暂不可用，本条为保底评分与摘要。
Limits of Confidence in Diffusion - Apple Machine Learning Research
research area
Methods and Algorithms
content type
paper
published
October 2026
Limits of Confidence in Diffusion
Authors Russ Webb, Amitis Shidani, Alice Bizeul, Dan Busbridge
View publication
Copy Bibtex
Discrete diffusion, including remasking and uniform-state samplers, generate a sequence by writing multiple token positions per step, drawing each from a per-position distribution and choosing which positions to write from those same distributions. For domains of general interest (pixels, phonemes, or words) there are inherent dependencies between tokens. We show that a step matches the training distribution only when the positions it writes are conditionally independent given the tokens already fixed, that no product of per-position distributions can match a dependent group, and that per-position distributions do not determine whether a group is dependent: two joint distributions can have identical per-position marginals while differing in which combinations of values occur. On ScanAndAdd, a synthetic task whose joint distribution is available in closed form, we verify that every group of two or more undetermined positions a confidence ranking writes is dependent, and measure the generated distribution to be 29Ã the sampling-noise floor total variation while per-sample metrics are 1.0.
Related readings and updates.
Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
July 9, 2026 research area Methods and Algorithms , research area Speech and Natural Language Processing
On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is beneficial and under which it is detrimental. Which teacher model should be used, and in the case of self-distillation, which specific context should serve as the supervisory signal? Does the optimal choice vary from one token to the next? At present, addressing these questions typicallyâ¦
Read more
Position Prediction as an Effective Pre-training Strategy
July 11, 2022 research area Methods and Algorithms conference ICML
Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing this representational capacity effectively requires a large amount of data, strong regularization, or both, to mitigate overfitting. Recently, the power of the Transformer has been unlocked by self-supervisedâ¦
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.
Work with us