AI Paper Atlas

Research map / Time series / Foundation models for time series

Rethinking Multimodal Time-Series Forecasting Evaluation

Haoxin Liu, Yichen Zhou, Rajat Sen, B. Aditya Prakash, Abhimanyu Das

ICML 2026 · Time series › Foundation models for time series · approach: LLM-based time series forecasting · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add calendar/date context to metadata (ablation)Gemini-2.0-Flash · Context-type ablationnormalized MASE: 0.787 -> 0.670Improved
add covariate context on top of metadata+date (ablation)Gemini-2.0-Flash · Context-type ablationnormalized MASE: 0.670 -> 0.674No clear effect
add event context on top of metadata+date (ablation)Gemini-2.0-Flash · Context-type ablationnormalized MASE: 0.670 -> 0.674No clear effect
add both events and covariates to metadata+date (ablation)Gemini-2.0-Flash · Context-type ablationnormalized MASE: 0.670 -> 0.650Improved
replace Time-MMD text context with TimesX-generated events (ablation)Gemini-2.0-Flash · Time-MMD (9 datasets)MASE: 0.906 -> 0.840Improved
evaluate after the LLM knowledge cutoff instead of beforeGemini-2.0-Flash · Search Trend (120 variables)MASE: 0.514 -> 0.594Hurt
evaluate after the LLM knowledge cutoff instead of beforeDeepSeek-V3 · Search Trend (120 variables)MASE: 0.606 -> 0.681Hurt
evaluate after cutoff instead of beforeTimesFM-2.5 · Search Trend (120 variables)MASE: 0.563 -> 0.573No clear effect
evaluate after cutoff instead of beforeMoirai-2.0 · Search Trend (120 variables)MASE: 0.691 -> 0.696No clear effect
average TimesFM-2.5 and Gemini-2.0-Flash forecastsensemble · TimesX (post-2024-07-01 horizons)normalized MASE: 0.645 -> 0.619Improved
have Gemini revise TimesFM-2.5 forecast via code (CodeRev)TimesFM-2.5 · TimesX (post-2024-07-01 horizons)normalized MASE: 0.645 -> 0.713Hurt
have Gemini revise TimesFM-2.5 forecast via text (TextRev)TimesFM-2.5 · TimesX (post-2024-07-01 horizons)normalized MASE: 0.645 -> 0.653No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy