Image de couverture de livre

Overcoming the Modality Gap in Context-Aided Forecasting

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zheng, Vincent Zhihao, Marcotte, Étienne, Ashok, Arjun, Williams, Andrew Robert, Sun, Lijun, Drouin, Alexandre, Zantedeschi, Valentina
Format:	Preprint
Publié:	2026
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

Beyond Naïve Prompting: Strategies for Improved Context-aided Forecasting with LLMs
par: Ashok, Arjun, et autres
Publié: (2025)

TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
par: Ashok, Arjun, et autres
Publié: (2023)

Dr-CiK: A Testbed for Foresight-Driven Agents
par: Tang, Yihong, et autres
Publié: (2026)

Context is Key: A Benchmark for Forecasting with Essential Textual Information
par: Williams, Andrew Robert, et autres
Publié: (2024)

Multivariate Probabilistic Time Series Forecasting with Correlated Errors
par: Zheng, Vincent Zhihao, et autres
Publié: (2024)

MVG-CRPS: A Robust Loss Function for Multivariate Probabilistic Forecasting
par: Zheng, Vincent Zhihao, et autres
Publié: (2024)

Probabilistic Traffic Forecasting with Dynamic Regression
par: Zheng, Vincent Zhihao, et autres
Publié: (2023)

Frequency-Constrained Learning for Long-Term Forecasting
par: Kong, Menglin, et autres
Publié: (2025)

Better Batch for Deep Probabilistic Time Series Forecasting
par: Zheng, Vincent Zhihao, et autres
Publié: (2023)

Dynamic Modes as Time Representation for Spatiotemporal Forecasting
par: Kong, Menglin, et autres
Publié: (2025)

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
par: Rasul, Kashif, et autres
Publié: (2023)

Scalable Dynamic Mixture Model with Full Covariance for Probabilistic Traffic Forecasting
par: Choi, Seongjin, et autres
Publié: (2022)

Learning to Defer for Causal Discovery with Imperfect Experts
par: Clivio, Oscar, et autres
Publié: (2025)

Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting
par: Garza, Azul, et autres
Publié: (2026)

Bound to Disagree: Generalization Bounds via Certifiable Surrogates
par: Bazinet, Mathieu, et autres
Publié: (2026)

Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses
par: Bazinet, Mathieu, et autres
Publié: (2024)

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting
par: Riachi, Roland, et autres
Publié: (2025)

Forecasting Residential Heating and Electricity Demand with Scalable, High-Resolution, Open-Source Models
par: Lee, Stephen J., et autres
Publié: (2025)

Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention
par: Zhan, Zhihao, et autres
Publié: (2025)

CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting
par: Tajeuna, Etienne, et autres
Publié: (2026)

Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures
par: Viallard, Paul, et autres
Publié: (2024)

Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs
par: Zantedeschi, Valentina, et autres
Publié: (2019)

Apriel-1.5-OpenReasoner: RL Post-Training for General-Purpose and Efficient Reasoning
par: Pardinas, Rafael, et autres
Publié: (2026)

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
par: Mofakhami, Mehrnaz, et autres
Publié: (2024)

Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
par: Wagenmaker, Andrew, et autres
Publié: (2024)

Overcoming the Stability Gap in Continual Learning
par: Harun, Md Yousuf, et autres
Publié: (2023)

Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale
par: Nie, Tong, et autres
Publié: (2023)

Nearest Neighbor Multivariate Time Series Forecasting
par: Zhang, Huiliang, et autres
Publié: (2025)

Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks
par: Leblanc, Benjamin, et autres
Publié: (2024)

Invariant Causal Set Covering Machines
par: Godon, Thibaud, et autres
Publié: (2023)

Intrinsic training dynamics of deep neural networks
par: Marcotte, Sibylle, et autres
Publié: (2025)

Transformative or Conservative? Conservation laws for ResNets and Transformers
par: Marcotte, Sibylle, et autres
Publié: (2025)

Online Linear Regression in Dynamic Environments via Discounting
par: Jacobsen, Andrew, et autres
Publié: (2024)

Error Adjustment Based on Spatiotemporal Correlation Fusion for Traffic Forecasting
par: Liu, Fuqiang, et autres
Publié: (2025)

Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
par: Jones, Erik, et autres
Publié: (2025)

Forecasting Sparse Movement Speed of Urban Road Networks with Nonstationary Temporal Matrix Factorization
par: Chen, Xinyu, et autres
Publié: (2022)

Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting
par: Yin, Tianyi, et autres
Publié: (2024)

When Context Is Not Enough: Modeling Unexplained Variability in Car-Following Behavior
par: Zhang, Chengyuan, et autres
Publié: (2025)

XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
par: Monteiro, João, et autres
Publié: (2024)

Overcoming Data Limitations in Internet Traffic Forecasting: LSTM Models with Transfer Learning and Wavelet Augmentation
par: Saha, Sajal, et autres
Publié: (2024)