Imagen de Portada

Feature Alignment: Rethinking Efficient Active Learning via Proxy in the Context of Pre-trained Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wen, Ziting, Pizarro, Oscar, Williams, Stefan
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Rethinking the Role of Proxy Rewards in Language Model Alignment
por: Kim, Sungdong, et al.
Publicado: (2024)

ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference
por: Li, Junjie, et al.
Publicado: (2026)

A Pre-trained Data Deduplication Model based on Active Learning
por: Shi, Haochen, et al.
Publicado: (2023)

Relational In-Context Learning via Synthetic Pre-training with Structural Prior
por: Wang, Yanbo, et al.
Publicado: (2026)

An Efficient Replay for Class-Incremental Learning with Pre-trained Models
por: Yin, Weimin, et al.
Publicado: (2024)

Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learning
por: Mattos, João, et al.
Publicado: (2026)

Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
por: Zhu, Yu, et al.
Publicado: (2024)

Sample Efficient Preference Alignment in LLMs via Active Exploration
por: Mehta, Viraj, et al.
Publicado: (2023)

Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
por: Song, Woomin, et al.
Publicado: (2024)

Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agent
por: Wang, Xinyuan, et al.
Publicado: (2024)

ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
por: Butler, Landon, et al.
Publicado: (2025)

Parallel Structures in Pre-training Data Yield In-Context Learning
por: Chen, Yanda, et al.
Publicado: (2024)

Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning
por: Chen, Yifang, et al.
Publicado: (2024)

Transfer Learning with Pre-trained Conditional Generative Models
por: Yamaguchi, Shin'ya, et al.
Publicado: (2022)

Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features
por: Kim, JaeYoon, et al.
Publicado: (2024)

IMU-1: Sample-Efficient Pre-training of Small Language Models
por: Grigorev, George
Publicado: (2026)

Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
por: Wang, Jiachen T., et al.
Publicado: (2025)

Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
por: Zhou, Weichao, et al.
Publicado: (2024)

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals
por: Pappalardo, Octavio
Publicado: (2026)

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
por: Lin, Xiaoqiang, et al.
Publicado: (2025)

Constraint-Informed Active Learning for End-to-End ACOPF Optimization Proxies
por: Li, Miao, et al.
Publicado: (2025)

Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuning
por: Ying, Wangyang, et al.
Publicado: (2024)

Efficient Process Reward Model Training via Active Learning
por: Duan, Keyu, et al.
Publicado: (2025)

Measuring Pre-training Data Quality without Labels for Time Series Foundation Models
por: Wen, Songkang, et al.
Publicado: (2024)

Pre-trained Large Language Models Learn Hidden Markov Models In-context
por: Dai, Yijia, et al.
Publicado: (2025)

Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model
por: Jin, Jiarui, et al.
Publicado: (2025)

Heterogeneity-Aware Coordination for Federated Learning via Stitching Pre-trained blocks
por: Zhan, Shichen, et al.
Publicado: (2024)

Federated Graph Learning with Structure Proxy Alignment
por: Fu, Xingbo, et al.
Publicado: (2024)

Utilizing Strategic Pre-training to Reduce Overfitting: Baguan -- A Pre-trained Weather Forecasting Model
por: Niu, Peisong, et al.
Publicado: (2025)

Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting
por: Tran, Trong Khiem, et al.
Publicado: (2026)

Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models
por: Ozyurt, Yilmazcan, et al.
Publicado: (2023)

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment
por: Chen, Zhikang, et al.
Publicado: (2025)

Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning
por: Piccoli, Elia, et al.
Publicado: (2025)

FedPFT: Federated Proxy Fine-Tuning of Foundation Models
por: Peng, Zhaopeng, et al.
Publicado: (2024)

Scaling Laws for Pre-training Agents and World Models
por: Pearce, Tim, et al.
Publicado: (2024)

OSF: On Pre-training and Scaling of Sleep Foundation Models
por: Shuai, Zitao, et al.
Publicado: (2026)

Pre-training Feature Guided Diffusion Model for Speech Enhancement
por: Yang, Yiyuan, et al.
Publicado: (2024)

Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language Models
por: Schröder, Christopher, et al.
Publicado: (2024)

FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
por: Fan, Tao, et al.
Publicado: (2026)

Pre-training with Synthetic Data Helps Offline Reinforcement Learning
por: Wang, Zecheng, et al.
Publicado: (2023)