AI Paper Atlas

Research map / Time series / Foundation models for time series

Can we generate portable representations for clinical time series data using LLMs?

Zongliang Ji, Yifei Sun, Andre Carlos Kajdacsy-Balla Amaral, Anna Goldenberg, Rahul G Krishnan

ICLR 2026 · Time series › Foundation models for time series · approach: Time-series language reasoning · 2 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
Replace grid imputation/TSDE/TimesFM inputs with LLM summarize-then-embed (Record2Vec)ICU downstream predictors · HiRID, MIMIC-IV, PPICU in-distributiontask metrics: best on 13 of 15 tasksImproved
Use Record2Vec instead of numeric baselines for cross-site transferHiRID/MIMIC-IV -> PPICU · Cross-site transfertask metrics: best in 10 of 10 columns (2 ties with TimesFM)Improved
Add LLM summarization before embedding (vs embedding raw serialization) (ablation)Record2Vec · Cross-site transfer (30 tasks)rank: no-summary concentrated in worst ranks; ~25x fewer tokensImproved
Add LLM summarization before embedding (vs raw serialization) (ablation)Record2Vec · In-distribution (15 tasks)rankNo clear effect
Use Llama-3.1 instead of Gemini-2.0 Flash or MedGemma as summarizer (ablation)Record2Vec · In-distribution and cross-siterankHurt
Vary prompt style (zero-shot, CoT, trend, ICD) (ablation)Record2Vec with Gemini-2.0 Flash · In-distribution and cross-siterank: slight edge for ICD prompts in transferNo clear effect
Replace LLM summary with fixed template (Record2Vec Template) (ablation)Record2Vec · HiRID -> PPICU mortality AUROCAUROC: 0.72 -> 0.72No clear effect
Replace LLM summary with fixed template (Record2Vec Template) (ablation)Record2Vec · MIMIC-IV -> PPICU length of stayMAE: 0.49 -> 0.77Hurt
Use Record2Vec embeddings rather than baselines for demographic probesRecord2Vec · Age/sex recoverabilityage MAE, genderNo clear effect
Few-shot fine-tune Record2Vec with 16 target samplesRecord2Vec · PPICU few-shot mortalityAUROCImproved
Use Record2Vec instead of TSDE on PPICU mortality in-distributionRecord2Vec · PPICU in-distributionMortality AUROC: 0.890 vs 0.890No 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