相关论文: Towards Machine Learning-Enabled Context Adaption …

Preference-aligned robot navigation in human environments is typically achieved through learning-based approaches, utilizing user feedback or demonstrations for personalization. However, personal preferences are subject to change and might…

This paper introduces Fast Linearized Adaptive Policy (FLAP), a new meta-reinforcement learning (meta-RL) method that is able to extrapolate well to out-of-distribution tasks without the need to reuse data from training, and adapt almost…

The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving model performance on a single downstream task. We consider a…

We propose a unified framework for adaptive routing in multitask, multimodal prediction settings where data heterogeneity and task interactions vary across samples. Motivated by applications in psychotherapy where structured assessments and…

A sequential decision process in which an adaptive radar system repeatedly interacts with a finite-state target channel is studied. The radar is capable of passively sensing the spectrum at regular intervals, which provides side information…

State-of-the-art meta reinforcement learning algorithms typically assume the setting of a single agent interacting with its environment in a sequential manner. A negative side-effect of this sequential execution paradigm is that, as the…

Large pre-trained language models are increasingly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT), but existing PEFT methods are typically deterministic and unimodal, making them poorly suited for low-resource…

In this paper, we present an adherence-aware reinforcement learning (RL) approach aimed at seeking optimal lane-changing recommendations within a semi-autonomous driving environment to enhance a single vehicle's travel efficiency. The…

In the era of Large Language Models (LLMs), Mixture-of-Experts (MoE) architectures offer a promising approach to managing computational costs while scaling up model parameters. Conventional MoE-based LLMs typically employ static Top-K…

With the growing connectivity demands, Unmanned Aerial Vehicles (UAVs) have emerged as a prominent component in the deployment of Next Generation On-demand Wireless Networks. However, current UAV positioning solutions typically neglect the…

Local navigation in cluttered environments often suffers from dense obstacles and frequent local minima. Conventional local planners rely on heuristics and are prone to failure, while deep reinforcement learning(DRL)based approaches provide…

Large language models (LLMs) often exhibit complementary strengths. Model routing harnesses these strengths by dynamically directing each query to the most suitable model, given a candidate model pool. However, routing performance relies on…

Wireless ad hoc networks are seldom characterized by one single performance metric, yet the current literature lacks a flexible framework to assist in characterizing the design tradeoffs in such networks. In this work, we address this…

Direct imaging of Earth-like exoplanets is one of the most prominent scientific drivers of the next generation of ground-based telescopes. Typically, Earth-like exoplanets are located at small angular separations from their host stars,…

Routing is the main part of wireless adhoc network conventionally there are two approaches first one is Proactive and another one is Reactive. Both these approaches have some substantial disadvantage and to overcome hybrid routing protocols…

Large Language Models (LLMs) have demonstrated remarkable abilities in various language tasks, making them promising candidates for decision-making in robotics. Inspired by Hierarchical Reinforcement Learning (HRL), we propose…

Combinatorial Optimization underpins many real-world applications and yet, designing performant algorithms to solve these complex, typically NP-hard, problems remains a significant research challenge. Reinforcement Learning (RL) provides a…

Offline reinforcement learning (RL) algorithms can learn better decision-making compared to behavior policies by stitching the suboptimal trajectories to derive more optimal ones. Meanwhile, Decision Transformer (DT) abstracts the RL as…

Low-rank adaptation (LoRA) and its mixture-of-experts (MOE) variants are highly effective parameter-efficient fine-tuning (PEFT) methods. However, they introduce significant latency in multi-tenant settings due to the LoRA modules and MOE…

Backpressure-based adaptive routing algorithms where each packet is routed along a possibly different path have been extensively studied in the literature. However, such algorithms typically result in poor delay performance and involve high…