Related papers: CoPEFT: Fast Adaptation Framework for Multi-Agent …

Existing Vehicle-to-Everything (V2X) cooperative perception methods rely on accurate multi-agent 3D annotations. Nevertheless, it is time-consuming and expensive to collect and annotate real-world data, especially for V2X systems. In this…

MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability…

This paper proposes a novel planning framework to handle a multi-agent pathfinding problem under team-connected communication constraint, where all agents must have a connected communication channel to the rest of the team during their…

Cooperative multi-agent systems require robust mechanisms for credit assignment under uncertainty. Here we introduce a variational framework, termed the Game-Theoretic Free Energy Principle (GT-FEP), that models coalition formation through…

The paper considers the problem of distributed adaptive linear parameter estimation in multi-agent inference networks. Local sensing model information is only partially available at the agents and inter-agent communication is assumed to be…

This paper presents CORE, a conceptually simple, effective and communication-efficient model for multi-agent cooperative perception. It addresses the task from a novel perspective of cooperative reconstruction, based on two key insights: 1)…

Transformer-based large pre-trained models have shown remarkable generalization ability, and various parameter-efficient fine-tuning (PEFT) methods have been proposed to customize these models on downstream tasks with minimal computational…

Aiming towards a holistic understanding of multiple downstream tasks simultaneously, there is a need for extracting features with better transferability. Though many latest self-supervised pre-training methods have achieved impressive…

In autonomous driving, recent research has increasingly focused on collaborative perception based on deep learning to overcome the limitations of individual perception systems. Although these methods achieve high accuracy, they rely on high…

Collaborative perception in multi-robot fleets is a way to incorporate the power of unity in robotic fleets. Collaborative perception refers to the collective ability of multiple entities or agents to share and integrate their sensory…

Despite the versatility of pre-trained language models (PLMs) across domains, their large memory footprints pose significant challenges in federated learning (FL), where the training model has to be distributed between a server and clients.…

Multi-label image classification demands adaptive training strategies to navigate complex, evolving visual-semantic landscapes, yet conventional methods rely on static configurations that falter in dynamic settings. We propose MAT-Agent, a…

Large language models (LLMs) have shown great potential in code-related tasks, yet open-source models lag behind their closed-source counterparts. To bridge this performance gap, existing methods generate vast amounts of synthetic data for…

Many hyperparameter optimization (HyperOpt) methods assume restricted computing resources and mainly focus on enhancing performance. Here we propose a novel cloud-based HyperOpt (CHOPT) framework which can efficiently utilize shared…

Collaborative perception empowers each agent to improve its perceptual ability through the exchange of perceptual messages with other agents. It inherently results in a fundamental trade-off between perception ability and communication…

Few-shot learning and parameter-efficient fine-tuning (PEFT) are crucial to overcome the challenges of data scarcity and ever growing language model sizes. This applies in particular to specialized scientific domains, where researchers…

Constrained multi-agent reinforcement learning offers the framework to design scalable and almost surely feasible solutions for teams of agents operating in dynamic environments to carry out conflicting tasks. We address the challenges of…

Transfer learning has become a popular task adaptation method in the era of foundation models. However, many foundation models require large storage and computing resources, which makes off-the-shelf deployment impractical. Post-training…

Inference-time computation is a critical yet challenging paradigm for enhancing the reasoning performance of large language models (LLMs). While existing strategies improve reasoning stability and consistency, they suffer from notable…

In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed…