相关论文: Revisiting LARS for Large Batch Training Generaliz…

Deep Multi-agent Reinforcement Learning (MARL) relies on neural networks with numerous parameters in multi-agent scenarios, often incurring substantial computational overhead. Consequently, there is an urgent need to expedite training and…

Training large language models (LLMs) poses challenges due to their massive scale and heterogeneous architectures. While adaptive optimizers like AdamW help address gradient variations, they still struggle with efficient and effective…

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

Recent developments in large language models have sparked interest in efficient pretraining methods. Stagewise training approaches to improve efficiency, like gradual stacking and layer dropping (Reddi et al, 2023; Zhang & He, 2020), have…

With the constant increase of available data in various domains, such as the Internet of Things, Social Networks or Smart Cities, it has become fundamental that agents are able to process and reason with such data in real time. Whereas…

The multi-robot adaptive sampling problem aims at finding trajectories for a team of robots to efficiently sample the phenomenon of interest within a given endurance budget of the robots. In this paper, we propose a robust and scalable…

Multi-Agent Reinforcement Learning (MARL) is a promising area of research that can model and control multiple, autonomous decision-making agents. During online training, MARL algorithms involve performance-intensive computations such as…

This study evaluates the performance of Large Language Models (LLMs) as an Artificial Intelligence-based tutor for a university course. In particular, different advanced techniques are utilized, such as prompt engineering,…

Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and…

Modern Large Language Models, such as the LLaMA, Qwen and DeepSeek series, predominantly adopt the Pre-LayerNorm (Pre-LN) Transformer architecture. While being stable during pretraining and scalable to large model sizes, Pre-LN suffers from…

Deep learning (DL) methods are widely used to extract high-dimensional patterns from the sequence features of radar echo signals. However, conventional DL algorithms face challenges such as redundant feature segments, and constraints from…

Large Language Models (LLMs) demonstrate promising capabilities in solving scientific problems but often suffer from the issue of hallucination. While integrating LLMs with tools can mitigate this issue, models fine-tuned on tool usage…

In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large number of CLs, each containing thousands of parameters, in…

Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling efforts. However, optimization practices in RL largely follow…

Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when…

Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces. However, these extended outputs often exhibit substantial…

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…

Sequential Recommendation (SR) aims to leverage the sequential patterns in users' historical interactions to accurately track their preferences. However, the primary reliance of existing SR methods on collaborative data results in…

Recent studies have shown that high disparities in effective learning rates (ELRs) across layers in deep neural networks can negatively affect trainability. We formalize how these disparities evolve over time by modeling weight dynamics…

Load shedding has been one of the most widely used and effective emergency control approaches against voltage instability. With increased uncertainties and rapidly changing operational conditions in power systems, existing methods have…