Copertina

Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dong, Yuxin, Jiang, Jiachen, Zhu, Zhihui, Ning, Xia
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

From Compression to Expression: A Layerwise Analysis of In-Context Learning
di: Jiang, Jiachen, et al.
Pubblicazione: (2025)

Learning to Adapt: In-Context Learning Beyond Stationarity
di: Qin, Zhen, et al.
Pubblicazione: (2026)

In-Context Learning for Non-Stationary MIMO Equalization
di: Jiang, Jiachen, et al.
Pubblicazione: (2025)

Task Vectors in In-Context Learning: Emergence, Formation, and Benefit
di: Yang, Liu, et al.
Pubblicazione: (2025)

Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
di: Jiang, Jiachen, et al.
Pubblicazione: (2025)

From Emergence to Control: Probing and Modulating Self-Reflection in Language Models
di: Zhu, Xudong, et al.
Pubblicazione: (2025)

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective
di: Han, Seungwook, et al.
Pubblicazione: (2024)

DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution
di: Jiang, Jiachen, et al.
Pubblicazione: (2026)

On the Convergence of Gradient Descent on Learning Transformers with Residual Connections
di: Qin, Zhen, et al.
Pubblicazione: (2025)

SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
di: Jiang, Jiachen, et al.
Pubblicazione: (2026)

Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
di: Jiang, Jiachen, et al.
Pubblicazione: (2024)

Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context
di: Cheng, Xiang, et al.
Pubblicazione: (2023)

Context and Diversity Matter: The Emergence of In-Context Learning in World Models
di: Wang, Fan, et al.
Pubblicazione: (2025)

NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation
di: Yang, Yuxin, et al.
Pubblicazione: (2026)

On Limitation of Transformer for Learning HMMs
di: Hu, Jiachen, et al.
Pubblicazione: (2024)

Enhancing Molecular Property Prediction with Auxiliary Learning and Task-Specific Adaptation
di: Dey, Vishal, et al.
Pubblicazione: (2024)

Provable In-Context Vector Arithmetic via Retrieving Task Concepts
di: Bu, Dake, et al.
Pubblicazione: (2025)

Towards Provable Emergence of In-Context Reinforcement Learning
di: Wang, Jiuqi, et al.
Pubblicazione: (2025)

Assessing the Limits of In-Context Learning beyond Functions using Partially Ordered Relation
di: Dutta, Debanjan, et al.
Pubblicazione: (2025)

Spoken Language Understanding on Unseen Tasks With In-Context Learning
di: Agrawal, Neeraj, et al.
Pubblicazione: (2025)

Mimic In-Context Learning for Multimodal Tasks
di: Jiang, Yuchu, et al.
Pubblicazione: (2025)

Strategy Coopetition Explains the Emergence and Transience of In-Context Learning
di: Singh, Aaditya K., et al.
Pubblicazione: (2025)

Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought
di: Xie, Zixuan, et al.
Pubblicazione: (2026)

Emergence of In-Context Reinforcement Learning from Noise Distillation
di: Zisman, Ilya, et al.
Pubblicazione: (2023)

Toward Multi-Fidelity Machine Learning Force Field for Cathode Materials
di: Dong, Guangyi, et al.
Pubblicazione: (2025)

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

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

Cat-AIR: Content and Task-Aware All-in-One Image Restoration
di: Jiang, Jiachen, et al.
Pubblicazione: (2025)

Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning
di: Müller, Jens, et al.
Pubblicazione: (2023)

On Fairness of Task Arithmetic: The Role of Task Vectors
di: Naganuma, Hiroki, et al.
Pubblicazione: (2025)

Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
di: Huang, Brandon, et al.
Pubblicazione: (2024)

The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards
di: Chen, Xi, et al.
Pubblicazione: (2024)

Learning to Order: Task Sequencing as In-Context Optimization
di: Kobiolka, Jan, et al.
Pubblicazione: (2026)

How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning
di: Wang, Entang, et al.
Pubblicazione: (2026)

In-Context Learning of Energy Functions
di: Schaeffer, Rylan, et al.
Pubblicazione: (2024)

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

On Task Vectors and Gradients
di: Zhou, Luca, et al.
Pubblicazione: (2025)

Understanding Generalization and Forgetting in In-Context Continual Learning
di: Li, Guangyu, et al.
Pubblicazione: (2026)

Personalized Vision via Visual In-Context Learning
di: Jiang, Yuxin, et al.
Pubblicazione: (2025)

Towards Understanding Feature Learning in Parameter Transfer
di: Yuan, Hua, et al.
Pubblicazione: (2025)