Image de couverture de livre

Revisiting LLMs as Zero-Shot Time-Series Forecasters: Small Noise Can Break Large Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Park, Junwoo, Lee, Hyuck, Lee, Dohyun, Gwak, Daehoon, Choo, Jaegul
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Self-Supervised Contrastive Learning for Long-term Forecasting
par: Park, Junwoo, et autres
Publié: (2024)

Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling
par: Gwak, Daehoon, et autres
Publié: (2024)

Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs
par: Gwak, Daehoon, et autres
Publié: (2025)

Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess
par: Hwang, Dongyoon, et autres
Publié: (2025)

Not the Example, but the Process: How Self-Generated Examples Enhance LLM Reasoning
par: Gwak, Daehoon, et autres
Publié: (2026)

Large Language Models Are Zero-Shot Time Series Forecasters
par: Gruver, Nate, et autres
Publié: (2023)

When Model Meets New Normals: Test-time Adaptation for Unsupervised Time-series Anomaly Detection
par: Kim, Dongmin, et autres
Publié: (2023)

Cross-RAG: Zero-Shot Retrieval-Augmented Time Series Forecasting via Cross-Attention
par: Lee, Seunghan, et autres
Publié: (2026)

Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning
par: Choi, Minseok, et autres
Publié: (2024)

Univariate to Multivariate: LLMs as Zero-Shot Predictors for Time-Series Forecasting
par: Madarasingha, Chamara, et autres
Publié: (2025)

ANT: Adaptive Noise Schedule for Time Series Diffusion Models
par: Lee, Seunghan, et autres
Publié: (2024)

MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs
par: Chatzigeorgakidis, Georgios, et autres
Publié: (2024)

Performance of Zero-Shot Time Series Foundation Models on Cloud Data
par: Toner, William, et autres
Publié: (2025)

EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models
par: Kim, Jinhee, et autres
Publié: (2024)

Zero-Shot Time Series Forecasting with Covariates via In-Context Learning
par: Auer, Andreas, et autres
Publié: (2025)

Zero Shot Time Series Forecasting Using Kolmogorov Arnold Networks
par: Bhattacharya, Abhiroop, et autres
Publié: (2024)

TiVaT: A Transformer with a Single Unified Mechanism for Capturing Asynchronous Dependencies in Multivariate Time Series Forecasting
par: Ha, Junwoo, et autres
Publié: (2024)

Sequential Order-Robust Mamba for Time Series Forecasting
par: Lee, Seunghan, et autres
Publié: (2024)

Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments
par: Chang, Junwoo, et autres
Publié: (2025)

Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport
par: Choi, Minseok, et autres
Publié: (2024)

Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification
par: Auer, Andreas, et autres
Publié: (2025)

Generalisation Bounds of Zero-Shot Economic Forecasting using Time Series Foundation Models
par: Jetwiriyanon, Jittarin, et autres
Publié: (2025)

Structured Noise Modeling for Enhanced Time-Series Forecasting
par: Koohfar, Sepideh
Publié: (2025)

Are Self-Attentions Effective for Time Series Forecasting?
par: Kim, Dongbin, et autres
Publié: (2024)

One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo
par: Shi, Hao-Nan, et autres
Publié: (2025)

Hyperspherical Normalization for Scalable Deep Reinforcement Learning
par: Lee, Hojoon, et autres
Publié: (2025)

QuiZSF: A Retrieval-Augmented Framework for Zero-Shot Time Series Forecasting
par: Ma, Shichao, et autres
Publié: (2025)

Adapting to the Unknown: Robust Meta-Learning for Zero-Shot Financial Time Series Forecasting
par: Liu, Anxian, et autres
Publié: (2025)

Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target
par: Kim, Taesan, et autres
Publié: (2026)

SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecasting
par: Huang, Ting-Ji, et autres
Publié: (2025)

Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models
par: Bhethanabhotla, Sathya Kamesh, et autres
Publié: (2024)

SVTime: Small Time Series Forecasting Models Informed by "Physics" of Large Vision Model Forecasters
par: Shen, ChengAo, et autres
Publié: (2025)

Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
par: Hwang, Dongyoon, et autres
Publié: (2024)

Zero-Shot Load Forecasting with Large Language Models
par: Liao, Wenlong, et autres
Publié: (2024)

TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
par: Lee, Jaebin, et autres
Publié: (2025)

Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks
par: Sohn, Jy-yong, et autres
Publié: (2024)

Do's and Don'ts: Learning Desirable Skills with Instruction Videos
par: Kim, Hyunseung, et autres
Publié: (2024)

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
par: Kim, Donghu, et autres
Publié: (2024)

DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning
par: Lee, Hyuck, et autres
Publié: (2026)

Channel-wise Retrieval for Multivariate Time Series Forecasting
par: Kang, Junhyeok, et autres
Publié: (2026)