Federated Learning (FL) has recently been applied to the parameter-efficient fine-tuning of Large Language Models (LLMs).

This paper presents an iterative approach for heterogeneous multi-agent route planning in environments with unknown resource distributions. We focus on a team of robots with diverse capabilities tasked with executing missions specified using Capability Temporal Logic (CaTL), a formal framework built on Signal Temporal Logic to handle spatial, temporal, capability, and resource constraints. The key challenge arises from the uncertainty in the initial distribution and quantity of resources in the environment. To address this, we introduce an iterative algorithm that dynamically balances exploration and task fulfillment. Robots are guided to explore the environment, identifying resource locations and quantities while progressively refining their understanding of the resource landscape. At the same time, they aim to maximally satisfy the mission objectives based on the current information, adapting their strategies as new data is uncovered. This approach provides a robust solution for planning in dynamic, resource-constrained environments, enabling efficient coordination of heterogeneous teams even under conditions of uncertainty. Our method's effectiveness and performance are demonstrated through simulated case studies.

Game-theoretic resource allocation on graphs (GRAG) involves two players competing over multiple steps to control nodes of interest on a graph, a problem modeled as a multi-step Colonel Blotto Game (MCBG). Finding optimal strategies is challenging due to the dynamic action space and structural constraints imposed by the graph. To address this, we formulate the MCBG as a Markov Decision Process (MDP) and apply Reinforcement Learning (RL) methods, specifically Deep Q-Network (DQN) and Proximal Policy Optimization (PPO). To enforce graph constraints, we introduce an action-displacement adjacency matrix that dynamically generates valid action sets at each step. We evaluate RL performance across a variety of graph structures and initial resource distributions, comparing against random, greedy, and learned RL policies. Experimental results show that both DQN and PPO consistently outperform baseline strategies and converge to a balanced $50\%$ win rate when competing against the learned RL policy. Particularly, on asymmetric graphs, RL agents successfully exploit structural advantages and adapt their allocation strategies, even under disadvantageous initial resource distributions.

Federated Learning (FL) has recently been applied to the parameter-efficient fine-tuning of Large Language Models (LLMs). While promising, it raises significant challenges due to the heterogeneous resources and data distributions of clients. This study introduces FlexLoRA, a simple yet effective aggregation scheme for LLM fine-tuning, which mitigates the ``bucket effect'' in traditional FL that restricts the potential of clients with ample resources by tying them to the capabilities of the least-resourced participants. FlexLoRA allows for dynamic adjustment of local LoRA ranks, fostering the development of a global model imbued with broader, less task-specific knowledge. By synthesizing a full-size LoRA weight from individual client contributions and employing Singular Value Decomposition (SVD) for weight redistribution, FlexLoRA fully leverages heterogeneous client resources. Involving thousands of clients performing heterogeneous NLP tasks and client resources, our experiments validate the efficacy of FlexLoRA, with the federated global model achieving consistently better improvement over SOTA FL methods in downstream NLP task performance across various heterogeneous distributions. FlexLoRA's practicality is further underscored by our theoretical analysis and its seamless integration with existing LoRA-based FL methods, offering a path toward cross-device, privacy-preserving federated tuning for LLMs.

Scheduling computational tasks represented by directed acyclic graphs (DAGs) is challenging because of its complexity. Conventional scheduling algorithms rely heavily on simple heuristics such as shortest job first (SJF) and critical path (CP), and are often lacking in scheduling quality. In this paper, we present a novel learning-based approach to scheduling DAG tasks. The algorithm employs a reinforcement learning agent to iteratively add directed edges to the DAG, one at a time, to enforce ordering (i.e., priorities of execution and resource allocation) of "tricky" job nodes. By doing so, the original DAG scheduling problem is dramatically reduced to a much simpler proxy problem, on which heuristic scheduling algorithms such as SJF and CP can be efficiently improved. Our approach can be easily applied to any existing heuristic scheduling algorithms. On the benchmark dataset of TPC-H, we show that our learning based approach can significantly improve over popular heuristic algorithms and consistently achieves the best performance among several methods under a variety of settings.

Recently, SpineNet has demonstrated promising results on object detection and image classification over ResNet model. However, it is unclear if the improvement adds up when combining scale-permuted backbone with advanced efficient operations and compound scaling. Furthermore, SpineNet is built with a uniform resource distribution over operations. While this strategy seems to be prevalent for scale-decreased models, it may not be an optimal design for scale-permuted models. In this work, we propose a simple technique to combine efficient operations and compound scaling with a previously learned scale-permuted architecture. We demonstrate the efficiency of scale-permuted model can be further improved by learning a resource distribution over the entire network. The resulting efficient scale-permuted models outperform state-of-the-art EfficientNet-based models on object detection and achieve competitive performance on image classification and semantic segmentation. Code and models will be open-sourced soon.

Much work in robotics and operations research has focused on optimal resource distribution, where an agent dynamically decides how to sequentially distribute resources among different candidates. However, most work ignores the notion of fairness in candidate selection. In the case where a robot distributes resources to human team members, disproportionately favoring the highest performing teammate can have negative effects in team dynamics and system acceptance. We introduce a multi-armed bandit algorithm with fairness constraints, where a robot distributes resources to human teammates of different skill levels. In this problem, the robot does not know the skill level of each human teammate, but learns it by observing their performance over time. We define fairness as a constraint on the minimum rate that each human teammate is selected throughout the task. We provide theoretical guarantees on performance and perform a large-scale user study, where we adjust the level of fairness in our algorithm. Results show that fairness in resource distribution has a significant effect on users' trust in the system.