Imagen de Portada

MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Jiapeng, Tian, Changxin, Chen, Kunlong, Liu, Ziqi, Mao, Jiaxin, Zhao, Wayne Xin, Zhang, Zhiqiang, Zhou, Jun
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training
por: Tian, Changxin, et al.
Publicado: (2025)

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
por: Wang, Jiapeng, et al.
Publicado: (2026)

Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models
por: Tian, Changxin, et al.
Publicado: (2025)

Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness
por: Chen, Sirui, et al.
Publicado: (2025)

SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling
por: Sun, Quanen, et al.
Publicado: (2026)

Towards Effective and Efficient Continual Pre-training of Large Language Models
por: Chen, Jie, et al.
Publicado: (2024)

MustoeLab/Publications: msDMS-MaP DOI
por: Khoa, et al.
Publicado: (2026)

H-MaP: An Iterative and Hybrid Sequential Manipulation Planner
por: Cicek, Berk, et al.
Publicado: (2024)

An Integrated Data Processing Framework for Pretraining Foundation Models
por: Sun, Yiding, et al.
Publicado: (2024)

BOSE: A Systematic Evaluation Method Optimized for Base Models
por: Luan, Hongzhi, et al.
Publicado: (2025)

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph
por: Jiang, Jinhao, et al.
Publicado: (2023)

Can Small Language Models be Good Reasoners for Sequential Recommendation?
por: Wang, Yuling, et al.
Publicado: (2024)

From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
por: Tan, Yuqiao, et al.
Publicado: (2026)

Multi-domain Knowledge Graph Collaborative Pre-training and Prompt Tuning for Diverse Downstream Tasks
por: Zhang, Yichi, et al.
Publicado: (2024)

Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data
por: Wang, Jiapeng, et al.
Publicado: (2025)

Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning
por: Wang, Xiaolei, et al.
Publicado: (2024)

MaP-AVR: A Meta-Action Planner for Agents Leveraging Vision Language Models and Retrieval-Augmented Generation
por: Guo, Zhenglong, et al.
Publicado: (2025)

G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks
por: Wan, Zhongwei, et al.
Publicado: (2022)

Re$^{\text{2}}$MaP: Macro Placement by Recursively Prototyping and Packing Tree-based Relocating
por: Shi, Yunqi, et al.
Publicado: (2025)

Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task
por: Zhao, Jinxu, et al.
Publicado: (2024)

SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection
por: Lu, Yi-Fan, et al.
Publicado: (2025)

Effectiveness of Pre-training for Few-shot Intent Classification
por: Zhang, Haode, et al.
Publicado: (2021)

MAQInstruct: Instruction-based Unified Event Relation Extraction
por: Xu, Jun, et al.
Publicado: (2025)

Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering
por: Tang, Xinyu, et al.
Publicado: (2025)

Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training
por: Luo, Zheheng, et al.
Publicado: (2024)

Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs?
por: Zeng, Hansi, et al.
Publicado: (2025)

RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library
por: Wang, Jiapeng, et al.
Publicado: (2025)

ChatUIE: Exploring Chat-based Unified Information Extraction using Large Language Models
por: Xu, Jun, et al.
Publicado: (2024)

Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward
por: Tang, Xinyu, et al.
Publicado: (2025)

Revealing the Learning Dynamics of Long-Context Continual Pre-training
por: Liang, Yupu, et al.
Publicado: (2026)

Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
por: Tang, Xinyu, et al.
Publicado: (2025)

Enhancing Cross-task Transfer of Large Language Models via Activation Steering
por: Tang, Xinyu, et al.
Publicado: (2025)

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

The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
por: Jin, Tian, et al.
Publicado: (2025)

Evaluating Discourse Cohesion in Pre-trained Language Models
por: He, Jie, et al.
Publicado: (2025)

VERITAS: A Unified Approach to Reliability Evaluation
por: Ramamurthy, Rajkumar, et al.
Publicado: (2024)

ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generation
por: Niu, Qingying, et al.
Publicado: (2026)

Visually Guided Generative Text-Layout Pre-training for Document Intelligence
por: Mao, Zhiming, et al.
Publicado: (2024)

Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering
por: Jiapeng, Li, et al.
Publicado: (2024)

Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models
por: Zhang, Fan, et al.
Publicado: (2024)