CausalPOI proposes a spatio-temporal graph causal learning method for cold-start POI check-in forecasting that builds functional interaction graphs and treatment-control pairs to outperform baselines on SafeGraph data.
hub Mixed citations
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
Mixed citation behavior. Most common role is background (67%).
38
Pith papers citing it
Background
67% of classified citations
abstract
Time series forecasting holds significant importance in many real-world dynamic systems and has been extensively studied. Unlike natural language process (NLP) and computer vision (CV), where a single large model can tackle multiple tasks, models for time series forecasting are often specialized, necessitating distinct designs for different tasks and applications. While pre-trained foundation models have made impressive strides in NLP and CV, their development in time series domains has been constrained by data sparsity. Recent studies have revealed that large language models (LLMs) possess robust pattern recognition and reasoning abilities over complex sequences of tokens. However, the challenge remains in effectively aligning the modalities of time series data and natural language to leverage these capabilities. In this work, we present Time-LLM, a reprogramming framework to repurpose LLMs for general time series forecasting with the backbone language models kept intact. We begin by reprogramming the input time series with text prototypes before feeding it into the frozen LLM to align the two modalities. To augment the LLM's ability to reason with time series data, we propose Prompt-as-Prefix (PaP), which enriches the input context and directs the transformation of reprogrammed input patches. The transformed time series patches from the LLM are finally projected to obtain the forecasts. Our comprehensive evaluations demonstrate that Time-LLM is a powerful time series learner that outperforms state-of-the-art, specialized forecasting models. Moreover, Time-LLM excels in both few-shot and zero-shot learning scenarios.
hub tools
citation-role summary
background 4
method 1
other 1
citation-polarity summary
representative citing papers
An LLM-agent system is proposed to revise statistical time series forecasts with weakly structured business context via tool use and constrained reasoning actions.
Olivia harmonizes time series datasets via normalized power spectral density using a Harmonizer module and resonator-based HarmonicAttention, achieving state-of-the-art zero-shot, few-shot, and full-shot forecasting on TSLib, GIFT-Eval, and GluonTS benchmarks.
Introduces the task of counterfactual time series forecasting with textual conditions plus a text-attribution mechanism that improves accuracy by distinguishing mutable from immutable factors.
TailedTS supplies 24.69 billion Wikipedia page-view records as a public benchmark for heavy-tailed time series forecasting and periodicity analysis, revealing weaker periodic structure in high-traffic pages.
LLaTiSA is a vision-language model trained on a new 83k-sample hierarchical time series reasoning dataset that shows superior performance and out-of-distribution generalization on stratified TSR tasks.
TimeSeriesExamAgent combines templates and LLM agents to generate scalable time series reasoning benchmarks, demonstrating that current LLMs have limited performance on both abstract and domain-specific tasks.
FeDPM learns and aligns local discrete prototypical memories across domains to create a unified discrete latent space for LLM-based time series foundation models in a federated setting.
A semi-synthetic augmentation creates the CAF-7M dataset and demonstrates that improved context data enables multimodal models to outperform unimodal baselines in context-aided forecasting.
Flow matching on time series targets a closed-form nonparametric velocity field that is a similarity-weighted mixture of observed transition velocities, making neural models approximations to an ideal memory-augmented dynamical system sampler.
TSVer is a new benchmark dataset for fact verification against time-series evidence, with 304 annotated real-world claims, 400 time series, verdicts, and justifications, plus baseline results showing current models struggle.
TS-Reasoner is a domain-oriented agent using LLMs, computational tools, and error feedback for multi-step time series inference, showing better performance than general LLMs on understanding and reasoning benchmarks.
This survey and benchmark of deep time series models using the released TSLib library finds that models with specific structures perform well only on distinct analysis tasks.
EpiEvolve achieves 0.629 accuracy in streaming COVID-19 forecasting by using episodic memory, reflection on delayed labels, and regime-aware retrieval, outperforming static LLMs (0.561) and CDC ensembles (0.325) while halving recovery lag after regime shifts.
MultiSeismo is a new multimodal seismic dataset with 16K events and SeisModal is a domain-adapted model that outperforms general multimodal models on seismic reasoning tasks.
TimeSRL uses semantic abstractions from time-series data optimized via reinforcement learning to achieve better cross-dataset generalization than standard ML or LLM baselines in mental health prediction.
Structured LLM agents correct agricultural yield forecasts from models like XGBoost, cutting MAE by 20-28% and MASE by up to 66% on strawberry and corn datasets.
GazeMind encodes gaze data for LLM reasoning to deliver interpretable, personalized cognitive load predictions that generalize across tasks without fine-tuning and outperform baselines by over 20% on a new 152-person dataset.
ST-PT turns transformers into explicit factor graphs for time series, enabling structural injection of symbolic priors, per-sample conditional generation, and principled latent autoregressive forecasting via MFVI iterations.
CAARL decomposes co-evolving time series into autoregressive segments, builds a temporal dependency graph, serializes it into a narrative, and uses LLMs for interpretable forecasting via chain-of-thought reasoning.
SC-LMKB uses LLM-generated data with cross-domain fusion to cut hallucinations and delivers up to 72.6% gains on cross-modality retrieval tasks over standard semantic communication.
The work introduces uncertainty-aware foundation models for clinical data by learning set-valued patient representations that enforce consistency across partial observations and integrate multimodal self-supervised objectives.
AlphaCast is a training-free LLM framework that performs interactive multi-stage reasoning for time series forecasting by integrating feature extraction, knowledge bases, case libraries, and contextual pools.
MAP4TS combines global, local, statistical, and temporal prompts derived from classical time-series analysis with raw embeddings via cross-modality alignment to improve LLM forecasting performance across eight datasets.
citing papers explorer
-
CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting
CausalPOI proposes a spatio-temporal graph causal learning method for cold-start POI check-in forecasting that builds functional interaction graphs and treatment-control pairs to outperform baselines on SafeGraph data.
-
Bridging the Last Mile of Time Series Forecasting with LLM Agents
An LLM-agent system is proposed to revise statistical time series forecasts with weakly structured business context via tool use and constrained reasoning actions.
-
Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density
Olivia harmonizes time series datasets via normalized power spectral density using a Harmonizer module and resonator-based HarmonicAttention, achieving state-of-the-art zero-shot, few-shot, and full-shot forecasting on TSLib, GIFT-Eval, and GluonTS benchmarks.
-
What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
Introduces the task of counterfactual time series forecasting with textual conditions plus a text-attribution mechanism that improves accuracy by distinguishing mutable from immutable factors.
-
TailedTS: Benchmark Dataset for Heavy-Tailed Time Series Prediction and Periodicity Quantification
TailedTS supplies 24.69 billion Wikipedia page-view records as a public benchmark for heavy-tailed time series forecasting and periodicity analysis, revealing weaker periodic structure in high-traffic pages.
-
LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
LLaTiSA is a vision-language model trained on a new 83k-sample hierarchical time series reasoning dataset that shows superior performance and out-of-distribution generalization on stratified TSR tasks.
-
TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale
TimeSeriesExamAgent combines templates and LLM agents to generate scalable time series reasoning benchmarks, demonstrating that current LLMs have limited performance on both abstract and domain-specific tasks.
-
Discrete Prototypical Memories for Federated Time Series Foundation Models
FeDPM learns and aligns local discrete prototypical memories across domains to create a unified discrete latent space for LLM-based time series foundation models in a federated setting.
-
Overcoming the Modality Gap in Context-Aided Forecasting
A semi-synthetic augmentation creates the CAF-7M dataset and demonstrates that improved context data enables multimodal models to outperform unimodal baselines in context-aided forecasting.
-
Is Flow Matching Just Trajectory Replay for Sequential Data?
Flow matching on time series targets a closed-form nonparametric velocity field that is a similarity-weighted mixture of observed transition velocities, making neural models approximations to an ideal memory-augmented dynamical system sampler.
-
EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts
EpiEvolve achieves 0.629 accuracy in streaming COVID-19 forecasting by using episodic memory, reflection on delayed labels, and regime-aware retrieval, outperforming static LLMs (0.561) and CDC ensembles (0.325) while halving recovery lag after regime shifts.
-
MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding
MultiSeismo is a new multimodal seismic dataset with 16K events and SeisModal is a domain-adapted model that outperforms general multimodal models on seismic reasoning tasks.
-
TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health
TimeSRL uses semantic abstractions from time-series data optimized via reinforcement learning to achieve better cross-dataset generalization than standard ML or LLM baselines in mental health prediction.
-
Agent-Based Post-Hoc Correction of Agricultural Yield Forecasts
Structured LLM agents correct agricultural yield forecasts from models like XGBoost, cutting MAE by 20-28% and MASE by up to 66% on strawberry and corn datasets.
-
GazeMind: A Gaze-Guided LLM Agent for Personalized Cognitive Load Assessment
GazeMind encodes gaze data for LLM reasoning to deliver interpretable, personalized cognitive load predictions that generalize across tasks without fine-tuning and outperform baselines by over 20% on a new 152-person dataset.
-
Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework
ST-PT turns transformers into explicit factor graphs for time series, enabling structural injection of symbolic priors, per-sample conditional generation, and principled latent autoregressive forecasting via MFVI iterations.
-
CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting
CAARL decomposes co-evolving time series into autoregressive segments, builds a temporal dependency graph, serializes it into a narrative, and uses LLMs for interpretable forecasting via chain-of-thought reasoning.
-
Semantic Communication with an LLM-enabled Knowledge Base
SC-LMKB uses LLM-generated data with cross-domain fusion to cut hallucinations and delivers up to 72.6% gains on cross-modality retrieval tasks over standard semantic communication.
-
Uncertainty-Aware Foundation Models for Clinical Data
The work introduces uncertainty-aware foundation models for clinical data by learning set-valued patient representations that enforce consistency across partial observations and integrate multimodal self-supervised objectives.
-
Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models
COM integrates geometric constraints into token initialization and training to preserve continuity and ordinality in time series tokens, improving token-based TS-LLM performance on benchmarks.
-
Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs
StockR1 unifies LLM-based financial reasoning and time-series forecasting by emitting verifiable forecast actions that condition a decoder, optimized via consistency-grounded RL to improve accuracy on QA and prediction tasks.
-
Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning
TCFT trains LLMs on temporal critique tasks to reduce post-cutoff knowledge leakage by 37-42 percentage points over prompting and standard SFT on Qwen models.
-
Heterogeneous Scientific Foundation Model Collaboration
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
-
Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction
A framework encodes observed trajectories and HD maps into tokens for frozen LLMs to perform spatio-temporal reasoning and predict future vehicle paths with a linear decoder.
-
A Review of Large Language Models for Stock Price Forecasting from a Hedge-Fund Perspective
This review synthesizes LLM uses in stock forecasting and catalogs key practical pitfalls from a hedge-fund viewpoint.
- TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning
- Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates