Search Results for author:
Found 8 papers, 4 papers with code
CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions
With instruction tuning, Large Language Models (LLMs) can enhance their ability to adhere to commands.
Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models
Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them.
3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset
Experimental results show that MMT models trained on our dataset exhibit a greater ability to exploit visual information than those trained on other MMT datasets.
Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?
The multimedia community has shown a significant interest in perceiving and representing the physical world with multimodal pretrained neural network models, and among them, the visual-language pertaining (VLP) is, currently, the most captivating topic.
Dynamic Contrastive Distillation for Image-Text Retrieval
Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts its deployment to real-world search scenarios (where the high latency is unacceptable).
Parameter-Efficient and Student-Friendly Knowledge Distillation
In this paper, we present a parameter-efficient and student-friendly knowledge distillation method, namely PESF-KD, to achieve efficient and sufficient knowledge transfer by updating relatively few partial parameters.
Where Does the Performance Improvement Come From? -- A Reproducibility Concern about Image-Text Retrieval
In contrast to previous works, we focus on the reproducibility of the approaches and the examination of the elements that lead to improved performance by pretrained and nonpretrained models in retrieving images and text.
Using Paxos to Build a Scalable, Consistent, and Highly Available Datastore
Compared to an eventually consistent datastore, we show that Spinnaker can be as fast or even faster on reads and only 5% to 10% slower on writes.
Databases Distributed, Parallel, and Cluster Computing
