Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Kai Zhen
AdaZeta: Adaptive zeroth-order tensor-train adaption for memory-efficient large language models fine-tuning
Fine-tuning large language models (LLMs) has achieved remarkable performance across various natural language processing tasks, yet it demands more and more memory as model sizes keep growing. To address this issue, the recently proposed Memory-efficient Zeroth-order (MeZO) methods attempt to fine-tune LLMs using only forward passes, thereby avoiding the need for a backpropagation graph. However, significant performance drops and a high risk of divergence have limited their widespread adoption.
Wanda++: Pruning large language models via regional gradients
Large Language Models (LLMs) pruning seeks to remove unimportant weights for inference speedup with minimal accuracy impact. However, existing methods often suffer from accuracy degradation without full-model sparsity-aware fine-tuning. This paper presents Wanda++, a novel pruning framework that outperforms the state-of-the-art methods by utilizing decoder-block-level regional gradients.
A better path to pruning large language models
In recent years, large language models (LLMs) have revolutionized the field of natural-language processing and made significant contributions to computer vision, speech recognition, and language translation. One of the keys to LLMs’ effectiveness has been the exceedingly large datasets they’re trained on. The trade-off is exceedingly large model sizes, which lead to slower runtimes and higher consumption of computational resources.
Wanda++: Pruning large language models via regional gradients
Large Language Models (LLMs) pruning seeks to remove unimportant weights for inference speedup with minimal performance impact. However, existing methods often suffer from performance loss without full-model sparsity-aware finetuning. This paper presents Wanda++, a novel pruning framework that outperforms the state-of-the-art methods by utilizing decoder-block-level regional gradients.
Sub-8-bit quantization aware training for 8-bit neural network accelerator with on device speech recognition
Job summaryWE ARE OPEN TO HIRING THIS ROLE IN SEATTLE, TORONTO, ARLINGTON, OR NYC.Amazon Advertising is one of Amazon's fastest growing and most profitable businesses, responsible for defining and delivering a collection of advertising products that drive discovery and sales. Our products and solutions are strategically important to enable our Retail and Marketplace businesses to drive long-term growth.
Sub-8-bit quantization for on-device speech recognition: a regularization-free approach
For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Among existing QAT methods, one major drawback is that the quantization centroids have to be predetermined and fixed.
Sparsification via compressed sensing for automatic speech recognition
In order to achieve high accuracy for machine learning (ML) applications, it is essential to employ models with a large number of parameters. Certain applications, such as Automatic Speech Recognition (ASR), however, require real-time interactions with users, hence compelling the model to have as low latency as possible. Deploying large scale ML applications thus necessitates model quantization and compression, especially when running ML models on resource constrained devices.
A systematic review and meta-analysis on effects of aerobic exercise in people with Parkinson’s disease
Journal List NPJ Parkinsons Dis v.8; 2022 PMC9622812 Kai Zhen,#1,2 Shiyan Zhang,#1,2 Xifeng Tao,2 Gen Li,2 Yuanyuan Lv,1,3 and Laikang Yu1,2 Kai Zhen 1Key Laboratory of Physical Fitness and Exercise, Ministry of Education, Beijing Sport University, Beijing, China 2Department of Sports Performance, Beijing Sport University, Beijing, China Shiyan Zhang 1Key Laboratory of Physical Fitness and Exercise, Ministry of Education, Beijing Sport University, Beijing, China 2Department of Sports...
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Kai
Contact Kai, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack