Related papers: Backpropagation-Free Multi-modal On-Device Model A…

This paper presents the winning approach for the 1st MultiModal Deception Detection (MMDD) Challenge at the 1st Workshop on Subtle Visual Computing (SVC). Aiming at the domain shift issue across source and target domains, we propose a…

Multi-task dense prediction, which aims to jointly solve tasks like semantic segmentation and depth estimation, is crucial for robotics applications but suffers from domain shift when deploying models in new environments. While unsupervised…

Modern embedded and cyber-physical systems require every day more performance, power efficiency and flexibility, to execute several profiles and functionalities targeting the ever growing adaptivity needs and preserving execution…

As modern software systems continue to grow in terms of complexity and volume, anomaly detection on multivariate monitoring metrics, which profile systems' health status, becomes more and more critical and challenging. In particular, the…

Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures composed of unimodal encoders, such as DINO and BERT, remains a significant challenge.…

This paper focuses on the Continual Test-Time Adaptation (CTTA) task, aiming to enable an agent to continuously adapt to evolving target domains while retaining previously acquired domain knowledge for effective reuse when those domains…

Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test-time adaptation (CTTA) directly adjusts a pre-trained…

Heterogeneity has become a mainstream architecture design choice for building High Performance Computing systems. However, heterogeneity poses significant challenges for achieving performance portability of execution. Adapting a program to…

Federated learning methods enable us to train machine learning models on distributed user data while preserving its privacy. However, it is not always feasible to obtain high-quality supervisory signals from users, especially for vision…

The federated learning (FL) framework enables edge clients to collaboratively learn a shared inference model while keeping privacy of training data on clients. Recently, many heuristics efforts have been made to generalize centralized…

A hybrid mobile/fixed device cloud that harnesses sensing, computing, communication, and storage capabilities of mobile and fixed devices in the field as well as those of computing and storage servers in remote datacenters is envisioned.…

Modern configurable software systems need to learn models that correlate configuration and performance. However, when the system operates in dynamic environments, the workload variations, hardware changes, and system updates will inevitably…

Multimodal depression detection is an important research topic that aims to predict human mental states using multimodal data. Previous methods treat different modalities equally and fuse each modality by na\"ive mathematical operations…

Federated fine-tuning (FedFT) provides an effective paradigm for fine-tuning large language models (LLMs) in privacy-sensitive scenarios. However, practical deployment remains challenging due to the limited resources on end devices.…

Pre-trained Vision-Language Models (VLMs), \textit{e.g.} CLIP, have become essential tools in multimodal transfer learning. However, fine-tuning VLMs in few-shot scenarios poses significant challenges in balancing task-specific adaptation…

With the advancement of mobile device capabilities, deploying reranking models directly on devices has become feasible, enabling real-time contextual recommendations. When migrating models from cloud to devices, resource heterogeneity…

To meet the practical requirements of low latency, low cost, and good privacy in online intelligent services, more and more deep learning models are offloaded from the cloud to mobile devices. To further deal with cross-device data…

We introduce CLARGA, a general-purpose multimodal fusion architecture for multimodal representation learning that works with any number and type of modalities without changing the underlying framework. Given a supervised dataset, CLARGA can…

In real-world scenarios, achieving domain adaptation and generalization poses significant challenges, as models must adapt to or generalize across unknown target distributions. Extending these capabilities to unseen multimodal…

This paper addresses the challenge of coordinating multi-robot systems under realistic communication delays using distributed optimization. We focus on consensus ADMM as a scalable framework for generating collision-free, dynamically…