PulseAugur
LIVE 11:14:01
ENTITY Generative models and uncertainty quantification 2023

Generative models and uncertainty quantification 2023

PulseAugur coverage of Generative models and uncertainty quantification 2023 — every cluster mentioning Generative models and uncertainty quantification 2023 across labs, papers, and developer communities, ranked by signal.

Total · 30d
0
0 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
0 over 90d
TIER MIX · 90D

No coverage in the last 90 days.

TIMELINE
  1. 2026-05-11 research_milestone A new paper details findings on how generative models learn rules across two distinct training timescales. source
  2. 2026-05-08 research_milestone A theoretical study proposes a method to prevent generative model collapse during retraining. source
SENTIMENT · 30D

3 day(s) with sentiment data

RECENT · PAGE 1/1 · 3 TOTAL
  1. RESEARCH · CL_30567 ·

    AI hallucinations in imaging linked to inverse problem limits

    Researchers have developed a theoretical framework to understand and quantify "hallucinations" in AI models used for inverse problems, such as medical imaging. The study shows that these realistic but incorrect details …

  2. TOOL · CL_27536 ·

    Generative models learn rules across two distinct training timescales

    Researchers have identified two distinct timescales in generative model training: the point at which generations become rule-valid ($\tau_{\mathrm{rule}}$) and the point at which models begin reproducing training sample…

  3. TOOL · CL_25561 ·

    AI models can avoid output collapse with diverse reward functions

    A new theoretical study explores how generative models can avoid collapsing into narrow output ranges during recursive retraining. Researchers propose that using multiple, diverse reward functions for data curation, rat…