Latest Articles for Model Training

Examining how soft labels enhance machine learning through dataset distillation.

Discussing methods to improve data management in training large AI models.

Twin-Merging improves model merging efficiency and adaptability across various tasks.

Learn how target unlearning safeguards privacy by allowing models to forget specific information.

A new framework addresses challenges in knowledge distillation for long-tailed data.

Introducing a flexible method for learning rates that enhances model performance without preset schedules.

This article reviews FS-GEN, combining large and small models for better outcomes.

DIPS addresses data quality issues in pseudo-labeling for better machine learning outcomes.

A new method improves example selection and instruction optimization for large language models.

A new benchmark for machine unlearning enhances evaluation and comparison of methods.

Examining how LLMs exhibit personality traits through new testing methods.

LoTA offers a smarter approach to adapting language models for multiple tasks.

A look at the role of complexity in model performance.

Exploring conservation laws and their role in complex machine learning scenarios.

Examining how normalization layers influence transformer performance and task handling.

This study focuses on enhancing model responses by targeting specific length requirements.

Improving data processing through knowledge sharing across different data types.

A look into the relationship between model size and training data efficiency.

A new approach enhances temperature adjustment in knowledge distillation for better model training.

Research reveals language models struggle with false reasoning, raising safety concerns.

This study breaks down how transformers utilize context in language prediction.

HyperLoader improves multi-task model training using innovative techniques and hypernetworks.

This article examines how small language models learn to handle noise in data.

Investigating how neural networks learn features during training.

This paper examines factors influencing neural networks' ability to generalize from data.

A look at the efficiency of GPT and RETRO in adapting language models with PEFT and RAG.

Masked diffusion models show promise in generative modeling for text and images.

This article explores overparameterization and its impact on model training efficiency.

Examining how training influences model performance in adversarial situations.

A new method minimizes misleading features in machine learning with less human effort.

This article discusses tackling model collapse using better data selection and feedback.

A study reveals key connections in how large language models function.

This study examines how initialization affects the finetuning of pretrained models using LoRA.

Learn how warmup can improve model training performance in deep learning.

A deep dive into how SGD optimizes model performance.

SPCL improves model training stability in multi-task environments.

New packing method enhances training speed and resource use in language models.

This article discusses retraining methods using model predictions for improved accuracy.

Research shows how MBR decoding enhances translation quality in smaller models.

Exploring how in-context probing and influence functions enhance data selection for models.