8 citations · 9 across the 8 of their papers we have counts for
4 papers · 1 filter
Mean-Field Parallel Decoding for Discrete Diffusion Language Models
Tamim Zoabi, Ameen Ali, Liran Ringel +1
Discrete diffusion language models enable parallel token generation, offering a pathway to low-latency decoding. However, selecting tokens independently by marginal confidence limi…
Semi-Supervised Risk Control via Prediction-Powered Inference
Bat-Sheva Einbinder, Liran Ringel, Yaniv Romano
The risk-controlling prediction sets (RCPS) framework is a general tool for transforming the output of any machine learning model to design a predictive rule with rigorous error ra…
Early Time Classification with Accumulated Accuracy Gap Control
Liran Ringel, Regev Cohen, Daniel Freedman +2
Early time classification algorithms aim to label a stream of features without processing the full input stream, while maintaining accuracy comparable to that achieved by applying…
Achieving Risk Control in Online Learning Settings
Shai Feldman, Liran Ringel, Stephen Bates +1
To provide rigorous uncertainty quantification for online learning models, we develop a framework for constructing uncertainty sets that provably control risk -- such as coverage o…