Related papers: MARS: Middleware for Adaptive Reflective Computer …
Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic workloads induce a temporal shift from single-turn inference to multi-turn LLM-tool loops,…
While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-improving frameworks attempt to bridge this gap but typically…
In this paper, we introduce MARS, a new scheduling system for HPC-cloud infrastructures based on a cost-aware, flexible reinforcement learning approach, which serves as an intermediate layer for next generation HPC-cloud resource manager.…
Runtime resource management for many-core systems is increasingly complex. The complexity can be due to diverse workload characteristics with conflicting demands, or limited shared resources such as memory bandwidth and power. Resource…
Reinforcement Learning (RL) has shown significant promise in automated portfolio management; however, effectively balancing risk and return remains a central challenge, as many models fail to adapt to dynamically changing market conditions.…
Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-date knowledge beyond their training data. We introduce MARS…
Along with the fast evolution of deep neural networks, the hardware system is also developing rapidly. As a promising solution achieving high scalability and low manufacturing cost, multi-accelerator systems widely exist in data centers,…
A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and…
Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this…
Heterogeneous multi-robot systems (HMRS) have emerged as a powerful approach for tackling complex tasks that single robots cannot manage alone. Current large-language-model-based multi-agent systems (LLM-based MAS) have shown success in…
Multimodal large language models (MLLMs) have shown remarkable capabilities in cross-modal understanding and reasoning, offering new opportunities for intelligent assistive systems, yet existing systems still struggle with risk-aware…
To enable Large Language Models (LLMs) to function as conscious agents with generalizable reasoning capabilities, it is crucial that they possess the reasoning ability to comprehend situational changes (transitions) in distribution…
Fine-tuning Multimodal Large Language Models (MLLMs) with parameter-efficient methods like Low-Rank Adaptation (LoRA) is crucial for task adaptation. However, imbalanced training dynamics across modalities often lead to suboptimal accuracy…
The next generation of many-core enabled large-scale computing systems relies on thousands of billions of heterogeneous processing cores connected to form a single computing unit. In such large-scale computing environments, resource…
Extreme dynamic heterogeneity in high performance computing systems and the convergence of traditional HPC with new simulation, analysis, and data science approaches impose increasingly more complex requirements on resource and job…
Implicit feedback is widely explored by modern recommender systems. Since the feedback is often sparse and imbalanced, it poses great challenges to the learning of complex interactions among users and items. Metric learning has been…
The growth of the Internet of Things has enabled a new generation of applications, pushing computation and intelligence toward the network edge. This trend, however, exposes challenges, as the heterogeneity of devices and the complex…
Known attempts to build autonomous robots rely on complex control architectures, often implemented with the Robot Operating System platform (ROS). Runtime adaptation is needed in these systems, to cope with component failures and with…
This paper describes some results of research on associate systems: knowledge-based systems that flexibly and adaptively support their human users in carrying out complex, time-dependent problem-solving tasks under uncertainty. Based on…
Memory bandwidth is critical in today's high performance computing systems. The bandwidth is particularly paramount for GPU workloads such as 3D Gaming, Imaging and Perceptual Computing, GPGPU due to their data-intensive nature. As the…