ICLR 2026PastTime series
1st ICLR Workshop on Time Series in the Age of Large Models
ICLR 2026 TSALM Workshop
- Submission deadline
- Feb 15, 2026, 12:00 UTCOpenReview-synced 2026-02-15 12:00 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (73)
Fetched from OpenReview (v2) on 2026-06-10.
A Learnable Wavelet Transformer for Long-Short Equity Trading and Risk-Adjusted Return Optimization
An Agentic Framework for Causal Discovery and Forecasting in Oil and Gas Time Series
APTGuard: An APT Detection Method Based on LLM and Time-Series Augmentation
ARFBench: Benchmarking Multimodal Time Series Reasoning for Software Incident Response
Auditing Black-Box Trends: Structural Inductive Bias Facilitates Causal Interpretability in Clinical Time Series
Balanced Latent Semantics and Signal Fidelity for EEG representation learning
Benchmarking LLM Summaries of Multimodal Clinical Time Series for Remote Monitoring
Beyond Earthbound Benchmarks: Evaluating Time Series Foundation Models on Satellite Telemetry Data
Beyond Fit & Predict: Forecasting API for the Foundation Model Era
Beyond Flat Taxonomies: Hierarchical Capability Profiling for Time-Series Understanding and Reasoning in Large Models
Beyond Statistical Changepoint Detection: Semantic Interpretation of Time Series via LLMs
Bridging the Fine-Tuning Gap in Time Series Classification with Synthetic Data and Inference Strategies
Cached Foundation Model Summaries for Memory-Efficient Clinical Time Series Inference
CLIC: Contextual Language-Informed Cardiac Pathology Classification
Complementing Domain Labels with WaveEnergy Signatures for Time Series Heterogeneity
Context-Informed Sequence Classification: A Multimodal Approach to Vehicle Diagnostics
Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models
Do Foundation Models Generalize to Real-World EV Fleets? A 1.1M-Drive Benchmark
Do We Need Domain-Specific Time-Series Models? Insights from EEG Classification Benchmarks
Does Normalization Choice Matter for Causal Large Time-Series Models?
DynLMC: Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series
EnergyX: An Agentic Framework for Explainable Energy Forecasting and Anomaly Detection
Expressive Power of Recurrent Spiking Neural Networks for Sequence Modeling
Factor Dimensionality and the Bias–Variance Tradeoff in Diffusion Portfolio Models
Finding the Zeitgeist in Time Series Foundation Models
Forecasting Solar Flares with the EVEREST Transformer
From Foundation Model to Tiny Time Series Classifier through Knowledge Distillation
From Noisy Neural Time Series to Structured Language: A Foundation Model for Imagined Speech Decoding from EEG signals
Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings
GPT2MEG: Quantizing MEG for Autoregressive Generation
Hindsight Preference Optimization for Financial Time Series Advisory
Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting
Improving Conditional Coverage in Time-Series Foundation Models via Direct Volatility Modeling
Interventional Time Series Priors for Causal Foundation Models
Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS
KeyTrend: Automated Keyword Synthesis via LLMs for Demand Forecasting with Google Trends
Large EEG Foundation Model Learns Informative Low-Frequency Representations from Intracranial Brain Signals
Learning to Query History: Nonstationary Classification via Learned Retrieval
Learning Transferable Sensor Models via Language-Informed Pretraining
LLM-Assisted Logic Rule Learning: Scaling Human Expertise for Time Series Anomaly Detection
LLM4Series: Structured Prompting for Time Series Forecasting with LLMs
Multi-Agent Framework for Developing and Evaluating Biometric-based Multimodal Synthetic Personas: A Case Study on Pregnancy and Postpartum Users
Narrative of Time across Scales (NoTS)
Non-Stationarity in the Embedding Space of Time Series Foundation Models
On the Role of Context in Zero-Shot Multivariate Time-Series Forecasting
Overcoming the Modality Gap in Context-Aided Forecasting
PETS: Inference-Time Differentially Private Synthetic Time Series Generation
PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning
ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series
Regimen-Aware Forecasting for Mechanistic Virtual Patients with Time-Series Foundation Models
Rethinking Multimodal Time-Series Forecasting Evaluation
Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting
STAMP: Shared-Dictionary Shapelet Tokenization For Multi-Resolution Time-Series Compression
State-Space Modeling in Natural Language
Status-Aware Self-Supervised Forecasting for Irregular Clinical Time Series
Structure-Aware Set Transformers: Temporal and Variable-type Attention Biases for Asynchronous Clinical Time Series
TF-JEPA: Predictive Alignment of Time–Frequency Representations Without Contrastive Pairs
The Arrow of Time: What Tabular Foundation Models Miss in Time Series Forecasting
The Geometry of Time-Series Diffusion: Why Latent Space Diffusion Works for Generation and Imputation
TiCT: A Synthetically Pre-Trained Foundation Model for Time Series Classification
Time Series Foundation Models Improve LLM Decisions: A Case Study in Stock Trading
Time-Series as Feedback: Evaluating Adaptive Reasoning in LLM Agents
Time-Series Foundation Model Embeddings as Means for Physiological Feature Extraction
TimEE: Towards End-to-end Time Series Classification via In-Context Learning
TimeSAE: Mechanistic Interpretability for Time-Series Foundation Models
TS-Arena: A Live Forecast Pre-Registration Platform for Leakage-Free Evaluation of Time Series Foundation Models
TS-Haystack: A Multi-Scale Retrieval Benchmark for Time Series Language Models
Tune-as-Inference: Amortized Configuration Learning for Time Series Foundation Models
UTICA: Multi-Objective Self-Distllation Fondation Model Pretraining for Time Series Classification
WaveFM: Wavelet Decomposition Masked Reconstruction for Multi-Scale Time-series Foundation Model
WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting
Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks
ZODIAC—ZERO-INFLATED OVERSHOOT CONTROLLED DUAL-HEAD INTEGRATION FOR ASYMMETRIC CROSS-DOMAIN FORECASTING