ICML 2025PastLarge language models
1st ICML Workshop on Foundation Models for Structured Data
FMSD @ ICML 2025
- Submission deadline
- May 24, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (70)
Fetched from OpenReview (v2) on 2026-06-10.
AdaRec: Adaptive Recommendation with LLMs via Narrative Profiling and Dual-Channel Reasoning
Are Time Series Foundation Models Ready for Zero-Shot Forecasting?
Assessing the Robustness of Tabular Prior-Data Fitted Network Classifier
Calibration Properties of Time Series Foundation Models
CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data only
Causal Foundation Models: Disentangling Physics from Instrument Properties
CLEAR: Contextual Logic-based Explanations for Anomaly Reasoning
ConTextTab: A Semantics-Aware Tabular In-Context Learner
Do Large Foundation Models Improve Time Series Segmentation? An Industrial Case Study in Oil and Gas Drilling
Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data
Do-PFN: In-Context Learning for Causal Effect Estimation
DriMM: Drilling Multimodal Model for Time-Series and Text in the Era of Large Models
Dual Adaptation of Time-Series Foundation Models for Financial Forecasting
Early Stopping Tabular In-Context Learning
Efficient Table Generation for Zero-Shot Column Type Annotation
Eliciting Numerical Predictive Distributions of LLMs Without Auto-Regression
Explore the Time Series Forecasting Potential of TabPFN Leveraging the Intrinsic Periodicity of Data
Exploring Relational Database Foundation Models from a Graph Perspective
Filter, Augment, Forecast: Online Data Selection for Robust Time Series Forecasting
FoMo-0D: A Foundation Model for Zero-shot Outlier Detection
Foundation Models for Clinical Records at Health System Scale
Foundation models for time series forecasting and policy evaluation in infectious disease epidemics: a modelling study
From Structured Data to Clinical Notes: Robust Clinical Decision Support with Fine-Tuned LLMs
From Tabular to Time Series: Can TabPFN Handle Mixed Data? A Study on PhysioNet
From Video Classification to Action Detection: Foundation vs. Task-Specific Models
G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
Gateformer: Advancing Multivariate Time Series Forecasting via Temporal and Variate-Wise Attention with Gated Representations
GATS: A Time-Series Dataset for Addressing General Aviation Flight Safety
GIT-BO: High-Dimensional Bayesian Optimization with Tabular Foundation Models
Improving Treatment Effect Estimation with LLM-Based Data Augmentation
In-context Pre-trained Time-Series Foundation Models adapt to Unseen Tasks
Instruction Tuning of Large Language Models for Tabular Data Generation—in One Day
LEAD - Framework for efficient time-series anomaly detection on large scale data using LLMs
Learning What Matters First: Sequential Adaptation of Time Series Foundation Models for Robust Financial Forecasting
Lights Out, Tabs On: Advancing Row-Column Encoding for Tabular LLMs
LLM Agents Struggle at Time Series Machine Learning Engineering
LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboard
Mantis: Lightweight Calibrated Foundation Model for User-Friendly Time Series Classification
MORPHEUS : A Foundation Model for Multivariate Time Series Forecasting
Multivariate Calibration is Performative: A Perspective on Pitfalls and Progress
Multivariate de Bruijn Graphs: A Symbolic Graph Framework for Time Series Forecasting
One-Run Privacy Auditing for Structured Generative and Foundation Models
Photoplethysmography, Foundation Models, Hypertension and Diabetes
Query, Don’t Train: Privacy-Preserving Tabular Prediction from EHR Data via SQL Queries
Random Initialization Can’t Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting
Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data
RECoRD: A Multi-Agent LLM Framework for Reverse Engineering Codebase to Relational Diagram
Rethinking Description Length: A TabPFN-Based Approximation of Bayesian Mixture Codes
Self-Imputation and Cross-Variable Learning Improve Water Quality Prediction with Sparse Data
Simulation-Based Pretraining and Domain Adaptation for Astronomical Time Series Tasks with Minimal Labeled Data
Soft Contrastive Learning for Irregular Multivariate Time Series
Speaking Numbers to LLMs: Multi-Wavelet Number Embeddings for Time Series Forecasting
State-Space Models for Tabular Prior-Data Fitted Networks
TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems
TabReason: A Reinforcement Learning-Enhanced Reasoning LLM for Explainable Tabular Data Prediction
TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representation
TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
TiRex: Zero-Shot Forecasting Across Long and Short Horizons
Toto: An Open Time Series Foundation Model Optimized for Observability
Toward Scientific Foundation Models for Aquatic Ecosystems
Towards a Multi-Modal Foundation Model for Inertial Confinement Fusion: Combining Structured Data and Diagnostic Images
Towards Benchmarking Foundation Models for Tabular Data With Text
Towards Fair In-Context Learning with Tabular Foundation Models
Towards Generalizable Multimodal ECG Representation Learning with LLM-extracted Clinical Entities
Towards Interpretable Time Series Foundation Models
Towards Synthetic Data for Fine-tuning Tabular Foundation Models
Two-Stage Contrastive Language Electrocardiogram Pre-training for Fine-Grained Waveform Features
W-LSTMix: A Hybrid Modular Forecasting Framework for Trend and Pattern Learning in Short-Term Load Forecasting
When and How Unlabeled Data Provably Improve In-Context Learning