Related papers: Pruning Foundation Models for High Accuracy withou…
Many neural network pruning algorithms proceed in three steps: train the network to completion, remove unwanted structure to compress the network, and retrain the remaining structure to recover lost accuracy. The standard retraining…
Structured pruning is essential for efficient deployment of Large Language Models (LLMs). The varying sensitivity of LLM sub-blocks to pruning necessitates the identification of optimal non-uniformly pruned models. Existing methods evaluate…
Vision-Language-Action (VLA) models have advanced robotic capabilities but remain challenging to deploy on resource-limited hardware. Pruning has enabled efficient compression of large language models (LLMs), yet it is largely understudied…
Model pruning is a performance optimization technique for large language models like R1 or o3-mini. However, existing pruning methods often lead to significant performance degradation or require extensive retraining and fine-tuning. This…
Large language models (LLMs) are computationally intensive. The computation workload and the memory footprint grow quadratically with the dimension (layer width). Most of LLMs' parameters come from the linear layers of the transformer…
Despite the impressive performance of large language models (LLMs), they often lag behind specialized models in various tasks. LLMs only use a fraction of the existing training data for in-context learning, while task-specific models…
Large Language Models (LLMs) achieve strong performance across diverse tasks but face prohibitive computational and memory costs. Pruning offers a promising path by inducing sparsity while preserving architectural flexibility. However,…
While various avenues of research have been explored for iterative pruning, little is known what effect pruning has on zero-shot test performance and its potential implications on the choice of pruning criteria. This pruning setup is…
Fueled by their remarkable ability to tackle diverse tasks across multiple domains, large language models (LLMs) have grown at an unprecedented rate, with some recent models containing trillions of parameters. This growth is accompanied by…
Weight binarization has emerged as a promising strategy to reduce the complexity of large language models (LLMs). Existing approaches fall into post-training binarization, which is simple but causes severe performance loss, and…
Oracle pruning, which selects unimportant weights by minimizing the pruned train loss, has been taken as the foundation for most neural network pruning methods for over 35 years, while few (if not none) have thought about how much the…
Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abundant works have been proposed to solve this problem with…
Neural network pruning has emerged as a promising approach for deploying LLMs in low-resource scenarios while preserving downstream task performance. However, for the first time, we reveal that such pruning disrupts LLMs' internal…
In AI research, the optimization of Large Language Models (LLMs) remains a significant challenge, crucial for advancing the field's practical applications and sustainability. Building upon the foundational work of Professor Song Han's lab…
While multimodal large language models demonstrate strong performance in complex reasoning tasks, they pose significant challenges related to model complexity during deployment, especially for resource-limited devices. In this paper, we…
Large language models (LLMs) consistently benefit from further fine-tuning on various tasks. However, we observe that directly tuning the Instruct (i.e., instruction-tuned) models often leads to marginal improvements and even performance…
With the rapid scaling of large language models (LLMs), structured pruning has become a widely used technique to learn efficient, smaller models from larger ones, delivering superior performance compared to training similarly sized models…
Since the release of GPT2-1.5B in 2019, the large language models (LLMs) have evolved from specialized deep models to versatile foundation models. While demonstrating remarkable zero-shot ability, the LLMs still require fine-tuning on local…
By removing parameters from deep neural networks, unstructured pruning methods aim at cutting down memory footprint and computational cost, while maintaining prediction accuracy. In order to tackle this otherwise intractable problem, many…
Network pruning focuses on algorithms that aim to reduce a given model's computational cost by removing a subset of its parameters while having minimal impact on performance. Throughout the last decade, the most widely used pruning paradigm…