Copertina

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Abedsoltan, Amirhesam, Zhang, Huaqing, Wen, Kaiyue, Lin, Hongzhou, Zhang, Jingzhao, Belkin, Mikhail
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Context-Scaling versus Task-Scaling in In-Context Learning
di: Abedsoltan, Amirhesam, et al.
Pubblicazione: (2024)

From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
di: Wen, Kaiyue, et al.
Pubblicazione: (2024)

On the Nystrom Approximation for Preconditioning in Kernel Machines
di: Abedsoltan, Amirhesam, et al.
Pubblicazione: (2023)

Fast training of large kernel models with delayed projections
di: Abedsoltan, Amirhesam, et al.
Pubblicazione: (2024)

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
di: Mallinar, Neil, et al.
Pubblicazione: (2022)

LinkD: AutoRegressive Diffusion Model for Mechanical Linkage Synthesis
di: Jadhav, Yayati, et al.
Pubblicazione: (2026)

SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation
di: Cheng, Shuang, et al.
Pubblicazione: (2025)

AutoRegressive Generation with B-rep Holistic Token Sequence Representation
di: Li, Jiahao, et al.
Pubblicazione: (2026)

Configuration-to-Performance Scaling Law with Neural Ansatz
di: Zhang, Huaqing, et al.
Pubblicazione: (2026)

MVAR: MultiVariate AutoRegressive Air Pollutants Forecasting Model
di: Fan, Xu, et al.
Pubblicazione: (2025)

Privacy Attacks on Image AutoRegressive Models
di: Kowalczuk, Antoni, et al.
Pubblicazione: (2025)

Bayesian Vector AutoRegression with Factorised Granger-Causal Graphs
di: Zhao, He, et al.
Pubblicazione: (2024)

NoiseAR: AutoRegressing Initial Noise Prior for Diffusion Models
di: Li, Zeming, et al.
Pubblicazione: (2025)

AMLNet: Adversarial Mutual Learning Neural Network for Non-AutoRegressive Multi-Horizon Time Series Forecasting
di: Lin, Yang
Pubblicazione: (2023)

When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks
di: Lo, Chung-Hsiang, et al.
Pubblicazione: (2026)

Task Aware Dreamer for Task Generalization in Reinforcement Learning
di: Ying, Chengyang, et al.
Pubblicazione: (2023)

Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning
di: Lovelace, Justin, et al.
Pubblicazione: (2026)

HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation
di: Zheng, Hongwei, et al.
Pubblicazione: (2025)

Can In-context Learning Really Generalize to Out-of-distribution Tasks?
di: Wang, Qixun, et al.
Pubblicazione: (2024)

Functionally Constrained Algorithm Solves Convex Simple Bilevel Problems
di: Zhang, Huaqing, et al.
Pubblicazione: (2024)

VARADE: a Variational-based AutoRegressive model for Anomaly Detection on the Edge
di: Mascolini, Alessio, et al.
Pubblicazione: (2024)

AdaPRL: Adaptive Pairwise Regression Learning with Uncertainty Estimation for Universal Regression Tasks
di: Liang, Fuhang, et al.
Pubblicazione: (2025)

Generating Auxiliary Tasks with Reinforcement Learning
di: Goldfeder, Judah, et al.
Pubblicazione: (2025)

Implementing Adaptations for Vision AutoRegressive Model
di: Shaikh, Kaif, et al.
Pubblicazione: (2025)

Distribution-dependent Generalization Bounds for Tuning Linear Regression Across Tasks
di: Balcan, Maria-Florina, et al.
Pubblicazione: (2025)

Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regression
di: Lyu, Junliang, et al.
Pubblicazione: (2024)

VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Bidding
di: Lv, Yiqin, et al.
Pubblicazione: (2025)

RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks
di: Penić, Rafael Josip, et al.
Pubblicazione: (2024)

From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers
di: Zhang, Dylan, et al.
Pubblicazione: (2024)

Variational Task Vector Composition
di: Zhang, Boyuan, et al.
Pubblicazione: (2025)

RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
di: Zhang, Jiaxing, et al.
Pubblicazione: (2023)

Task Shift: From Classification to Regression in Overparameterized Linear Models
di: LaBonte, Tyler, et al.
Pubblicazione: (2025)

IM-Context: In-Context Learning for Imbalanced Regression Tasks
di: Nejjar, Ismail, et al.
Pubblicazione: (2024)

Intrinsic Task Symmetry Drives Generalization in Algorithmic Tasks
di: Hwang, Hyeonbin, et al.
Pubblicazione: (2026)

Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks
di: Wiedemer, Thaddäus, et al.
Pubblicazione: (2025)

Task-Agnostic Experts Composition for Continual Learning
di: Quarantiello, Luigi, et al.
Pubblicazione: (2025)

Multi-Task Learning for Routing Problem with Cross-Problem Zero-Shot Generalization
di: Liu, Fei, et al.
Pubblicazione: (2024)

Symbolic Regression as Feature Engineering Method for Machine and Deep Learning Regression Tasks
di: Shmuel, Assaf, et al.
Pubblicazione: (2023)

MLPs Learn In-Context on Regression and Classification Tasks
di: Tong, William L., et al.
Pubblicazione: (2024)

AutoTask: Task Aware Multi-Faceted Single Model for Multi-Task Ads Relevance
di: Guo, Shouchang, et al.
Pubblicazione: (2024)