Latest Articles for Model Optimization

OGEN enhances vision-language models' ability to recognize new classes effectively.

This article reviews techniques to enhance Large Language Models' efficiency and performance.

A method for speeding up large language models without sacrificing output quality.

Introducing DE-BERT, a framework improving efficiency in language models through early exiting strategies.

A method for fine-tuning language models using fewer parameters.

Learn how new techniques improve the efficiency of large machine learning models.

Introducing BMTPT for improved prompt tuning in language models.

SLEB streamlines LLMs by removing redundant transformer blocks, enhancing speed and efficiency.

LoRETTA improves fine-tuning efficiency for large language models with fewer parameters.

A new approach to make language models smaller and faster using 1-bit quantization.

A new method for selecting demonstrations enhances model performance in language tasks.

New methods promise better AI model performance through simplified reinforcement learning.

New quantization method enhances performance of large language models while reducing size.

New techniques enhance quantization while managing outliers for better model performance.

A study on efficient methods for fine-tuning large models through Low-Rank Adaptation.

A new method enhances image generation accuracy using vision-language models.

Exploring new methods to enhance decision-making in learning agents.

Research reveals how flat minima relate to better model performance on unseen data.

A new method to make RAG faster and improve quality.

A new approach enhances model performance across diverse data types.

Investigating model compression methods to improve efficiency and defenses against attacks.

FedMef improves federated learning for low-resource devices through innovative pruning techniques.

MetaOptimize improves model performance by adjusting learning settings dynamically.

Introducing a new method for efficient model fine-tuning.

A new method uses reinforcement learning to prune CNNs while training.

This paper discusses the costs and improvements for low-precision neural networks.

Generalized Diffusion Adaptation improves model performance with out-of-distribution samples.

Strategies for improving variational autoencoders in handling incomplete datasets.

A method to improve language model performance across diverse languages during compression.

Introducing a method for task-agnostic pruning of complex models.

A new method enhances multimodal models using shared visual prompts.

A new method to improve model performance in AI through knowledge transfer.

A new method, InsTa, enhances task selection in instruction tuning.

This study evaluates how model size and quantization impact language model performance.

New techniques improve efficiency and accuracy in large language models.

Enhancing diffusion models by adding LoRA to attention layers for better images.

A new method for improving model structures more effectively and efficiently.

This paper presents EFRAP, a defense against quantization-conditioned backdoor attacks in deep learning models.

A new method enhances fine-tuning of large models using spectral information.

A method combining low-rank and orthogonal adaptations for AI models.