相关论文: InfoCom: Kilobyte-Scale Communication-Efficient Co…

As digital technologies advance, communication networks face challenges in handling the vast data generated by intelligent devices. Autonomous vehicles, smart sensors, and IoT systems necessitate new paradigms. This thesis addresses these…

Concept Bottleneck Models (CBMs) try to make the decision-making process transparent by exploring an intermediate concept space between the input image and the output prediction. Existing CBMs just learn coarse-grained relations between the…

Communication is essential in coordinating the behaviors of multiple agents. However, existing methods primarily emphasize content, timing, and partners for information sharing, often neglecting the critical aspect of integrating shared…

Information Bottlenecks (IBs) learn representations that generalize to unseen data by information compression. However, existing IBs are practically unable to guarantee generalization in real-world scenarios due to the vacuous…

In next-generation wireless networks, supporting real-time applications such as augmented reality, autonomous driving, and immersive Metaverse services demands stringent constraints on bandwidth, latency, and reliability. Existing semantic…

Maintaining efficient semantic representations of the environment is a major challenge both for humans and for machines. While human languages represent useful solutions to this problem, it is not yet clear what computational principle…

Deep learning algorithms have recently gained significant attention due to their impressive performance. However, their high complexity and un-interpretable mode of operation hinders their confident deployment in real-world safety-critical…

Recent trend towards increasing large machine learning models require both training and inference tasks to be distributed. Considering the huge cost of training these models, it is imperative to unlock optimizations in computation and…

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically…

This paper presents a comprehensive end-to-end evaluation of an infrastructure-assisted collective perception (ICP) system deployed on a highway using ITS-G5 technology. Open-road tests were conducted in the Bizkaia Connected Corridor…

In this paper, we study the framework of collaborative inference, or edge ensembles. This framework enables multiple edge devices to improve classification accuracy by exchanging intermediate features rather than raw observations. However,…

Collaborative perception shares information among different agents and helps solving problems that individual agents may face, e.g., occlusions and small sensing range. Prior methods usually separate the multi-agent fusion and multi-time…

Collaborative perception has garnered significant attention as a crucial technology to overcome the perceptual limitations of single-agent systems. Many state-of-the-art (SOTA) methods have achieved communication efficiency and high…

Wireless connectivity has traditionally been regarded as an opaque data pipe carrying messages, whose context-dependent meaning and effectiveness have been ignored. Nevertheless, in emerging cyber-physical and autonomous networked systems,…

Learning effective joint embedding for cross-modal data has always been a focus in the field of multimodal machine learning. We argue that during multimodal fusion, the generated multimodal embedding may be redundant, and the discriminative…

The idea of cooperative perception is to benefit from shared perception data between multiple vehicles and overcome the limitations of on-board sensors on single vehicle. However, the fusion of multi-vehicle information is still challenging…

Mobile manipulation is a fundamental capability for general-purpose robotic agents, requiring both coordinated control of the mobile base and manipulator and robust perception under dynamically changing viewpoints. However, existing…

In the past decade, although single-robot perception has made significant advancements, the exploration of multi-robot collaborative perception remains largely unexplored. This involves fusing compressed, intermittent, limited,…

For modern recommender systems, the use of low-dimensional latent representations to embed users and items based on their observed interactions has become commonplace. However, many existing recommendation models are primarily designed for…

Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human…