相关论文: E2ETune: End-to-End Knob Tuning via Fine-tuned Gen…

We present a novel end-to-end trainable neural network model for task-oriented dialog systems. The model is able to track dialog state, issue API calls to knowledge base (KB), and incorporate structured KB query results into system…

Most state-of-the-art information extraction approaches rely on token-level labels to find the areas of interest in text. Unfortunately, these labels are time-consuming and costly to create, and consequently, not available for many…

While deep neural networks have demonstrated remarkable performance across various tasks, they typically require massive training data. Due to the presence of redundancies and biases in real-world datasets, not all data in the training…

Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions. This impairs their performance in complex problems whose solution consists of multiple…

Pre-training and fine-tuning is a paradigm for alleviating the data scarcity problem in end-to-end speech translation (E2E ST). The commonplace "modality gap" between speech and text data often leads to inconsistent inputs between…

Keyword spotting (KWS) enables speech-based user interaction and gradually becomes an indispensable component of smart devices. Recently, end-to-end (E2E) methods have become the most popular approach for on-device KWS tasks. However, there…

Fine-tuning facilitates the adaptation of text-to-image generative models to novel concepts (e.g., styles and portraits), empowering users to forge creatively customized content. Recent efforts on fine-tuning focus on reducing training data…

Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder…

Retrieval-augmented generation methods often neglect the quality of content retrieved from external knowledge bases, resulting in irrelevant information or potential misinformation that negatively affects the generation results of large…

Most large web-scale applications are now built by composing collections (from a few up to 100s or 1000s) of microservices. Operators need to decide how many resources are allocated to each microservice, and these allocations can have a…

In this paper we tackle a fundamental question: "Can we train latent diffusion models together with the variational auto-encoder (VAE) tokenizer in an end-to-end manner?" Traditional deep-learning wisdom dictates that end-to-end training is…

Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes increasingly costly. Parameter-efficient fine-tuning methods…

Large language models (LLMs) excel at generating contextually relevant content. However, tailoring these outputs to individual users for effective personalization is a significant challenge. While rich user-specific information often exists…

Traditional recommender systems heavily rely on ID features, which often encounter challenges related to cold-start and generalization. Modeling pre-extracted content features can mitigate these issues, but is still a suboptimal solution…

We propose a Coefficient-to-Basis Network (C2BNet), a novel framework for solving inverse problems within the operator learning paradigm. C2BNet efficiently adapts to different discretizations through fine-tuning, using a pre-trained model…

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer from two critical limitations: (1) inefficient token-to-expert…

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning…

The current state-of-the-art (SOTA) for automated text-to-SQL still falls well short of expert human performance as measured by execution accuracy (EX) on the BIRD-SQL benchmark. The most accurate methods are also slow and expensive. To…

End-to-end speech translation, a hot topic in recent years, aims to translate a segment of audio into a specific language with an end-to-end model. Conventional approaches employ multi-task learning and pre-training methods for this task,…

Advanced compiler technology is crucial for enabling machine learning applications to run on novel hardware, but traditional compilers fail to deliver performance, popular auto-tuners have long search times and expert-optimized libraries…