Related papers: DUET: A Tuning-Free Device-Cloud Collaborative Par…
Device-cloud collaboration holds promise for deploying large language models (LLMs), leveraging lightweight on-device models for efficiency while relying on powerful cloud models for superior reasoning. A central challenge in this setting…
Recent advances in decentralized deep learning algorithms have demonstrated cutting-edge performance on various tasks with large pre-trained models. However, a pivotal prerequisite for achieving this level of competitiveness is the…
Serving disaggregated large language models has been widely adopted in industrial practice for enhanced performance. However, too many tokens generated in decoding phase, i.e., occupying the resources for a long time, essentially hamper the…
The demise of Moore's Law has led to the rise of hardware acceleration. However, the focus on accelerating stable algorithms in their entirety neglects the abundant fine-grained acceleration opportunities available in broader domains and…
Deep learning models are being deployed in many mobile intelligent applications. End-side services, such as intelligent personal assistants, autonomous cars, and smart home services often employ either simple local models on the mobile or…
Deep Learning (DL) model-based AI services are increasingly offered in a variety of predictive analytics services such as computer vision, natural language processing, speech recognition. However, the quality of the DL models can degrade…
Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…
The distribution shifts between training and test data typically undermine the performance of models. In recent years, lots of work pays attention to domain generalization (DG) where distribution shifts exist, and target data are unseen.…
On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized. With this end, we propose…
Despite the remarkable generation capabilities of Diffusion Models (DMs), conducting training and inference remains computationally expensive. Previous works have been devoted to accelerating diffusion sampling, but achieving data-efficient…
UML and ER diagrams are foundational in computer science education but come with challenges for learners due to the need for abstract thinking, contextual understanding, and mastery of both syntax and semantics. These complexities are…
Pervasive mobile AI applications primarily employ one of the two learning paradigms: cloud-based learning (with powerful large models) or on-device learning (with lightweight small models). Despite their own advantages, neither paradigm can…
The domain shift between training and testing data presents a significant challenge for training generalizable deep learning models. As a consequence, the performance of models trained with the independent and identically distributed…
Multi-task learning has garnered widespread attention in the industry due to its efficient data utilization and strong generalization capabilities, making it particularly suitable for providing high-quality intelligent services to users.…
This paper investigates the 3D domain generalization (3DDG) ability of large 3D models based on prevalent prompt learning. Recent works demonstrate the performances of 3D point cloud recognition can be boosted remarkably by…
We propose $\textbf{UniDG}$, a novel and $\textbf{Uni}$fied framework for $\textbf{D}$omain $\textbf{G}$eneralization that is capable of significantly enhancing the out-of-distribution generalization performance of foundation models…
Foundation models (FoMos), referring to large-scale AI models, possess human-like capabilities and are able to perform competitively in the domain of human intelligence. The breakthrough in FoMos has inspired researchers to deploy such…
Deep learning models often struggle to maintain performance when deployed on data distributions different from their training data, particularly in real-world applications where environmental conditions frequently change. While Multi-source…
Specializing LLMs in various domain-specific tasks has emerged as a critical step towards achieving high performance. However, the construction and annotation of datasets in specific domains are always very costly. Apart from using superior…
Domain generalization (DG) aims at learning a model on source domains to well generalize on the unseen target domain. Although it has achieved great success, most of existing methods require the label information for all training samples in…