Good Papers: read the good ones

TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning

TimeClaw learns reusable hierarchical experience from exploratory time-series executions via explore-compare-distill-reinject loops, improving reasoning without online adaptation.

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 0/5

80%Must read

?Must readVote to see the score

NeurIPS 2026The University of Tokyo Harbin Institute of Technology Tokyo Time series forecasting

DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting

DiffPTS reformulates diffusion ELBO under a location-scale noise model to unify estimator training and diffusion via joint optimization, achieving state-of-the-art probabilistic forecasting with over 14.53% CRPS and 16.55% MSE reductions.

Weiwei Ye, Dongyuan Li, Hangchen Liu, Haotong Jiang and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 3/5

medium 8/10

strict 1/5