Related papers: MeCo: Enhancing LLM-Empowered Multi-Robot Collabor…
The recent progress of AI can be largely attributed to large language models (LLMs). However, their escalating memory requirements introduce challenges for machine learning (ML) researchers and engineers. Addressing this requires developers…
Multi-Task Learning (MTL) aims to boost predictive performance by sharing information across related tasks, yet conventional methods often suffer from negative transfer when unrelated or noisy tasks are forced to share representations. We…
In multi-robot systems, achieving coordinated missions remains a significant challenge due to the coupled nature of coordination behaviors and the lack of global information for individual robots. To mitigate these challenges, this paper…
Large Language Models (LLMs) deliver strong performance but incur high inference cost in real-world services, especially under workloads with repeated or near-duplicate queries across users and sessions. In this work, we propose MemBoost, a…
Large Language Models (LLMs) have advanced rapidly in recent years, demonstrating strong capabilities in problem comprehension and reasoning. Inspired by these developments, researchers have begun exploring the use of LLMs as decentralized…
Recent advancements in Large Language Models (LLMs) have demonstrated substantial capabilities in enhancing communication and coordination in multi-robot systems. However, existing methods often struggle to achieve efficient collaboration…
Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While…
In this work, we introduce SMART-LLM, an innovative framework designed for embodied multi-robot task planning. SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models (LLMs), harnesses the power of LLMs to convert…
This paper presents a novel approach to enhance autonomous robotic manipulation using the Large Language Model (LLM) for logical inference, converting high-level language commands into sequences of executable motion functions. The proposed…
Modern deployment of large language models (LLMs) frequently involves both inference serving and continuous retraining to stay aligned with evolving data and user feedback. Common practices separate these workloads onto distinct servers in…
Effective human-robot collaboration hinges on robust communication channels, with visual signaling playing a pivotal role due to its intuitive appeal. Yet, the creation of visually intuitive cues often demands extensive resources and…
Rapid advancements in artificial intelligence (AI) have enabled robots to performcomplex tasks autonomously with increasing precision. However, multi-robot systems (MRSs) face challenges in generalization, heterogeneity, and safety,…
This paper introduces CoMuRoS (Collaborative Multi-Robot System), a generalizable hierarchical architecture for heterogeneous robot teams that unifies centralized deliberation with decentralized execution, and supports event-driven…
Effective robotic systems for long-horizon human-robot collaboration must adapt to a wide range of human partners, whose physical behavior, willingness to assist, and understanding of the robot's capabilities may change over time. This…
Fine-tuning a task-specific multilingual large language model (LLM) involves training the model on a multilingual dataset with examples in all the required languages. Updating one or more supported languages with additional data or adding…
Navigating complex environments requires robots to effectively store observations as memories and leverage them to answer human queries about spatial locations, which is a critical yet underexplored research challenge. While prior work has…
Nowadays, Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications. However, long context training poses great challenges considering the constraint of GPU memory. It not only leads…
Model merging is a flexible and computationally tractable approach to merge single-task checkpoints into a multi-task model. Prior work has solely focused on constrained multi-task settings where there is a one-to-one mapping between a…
We envision a continuous collaborative learning system where groups of LLM agents work together to solve reasoning problems, drawing on memory they collectively build to improve performance as they gain experience. This work establishes the…
Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits…