While large language models (LLMs) have become the de facto framework for literature-related tasks, they still struggle to function as domain-specific literature agents due to their inability to connect pieces of knowledge and reason across domain-specific contexts, terminologies, and nomenclatures. This challenge underscores the need for a tool that facilitates such domain-specific adaptation and enables rigorous benchmarking across literature tasks. To that end, we introduce LitBench, a benchmarking tool designed to enable the development and evaluation of domain-specific LLMs tailored to literature-related tasks. At its core, LitBench uses a data curation process that generates domain-specific literature sub-graphs and constructs training and evaluation datasets based on the textual attributes of the resulting nodes and edges. The tool is designed for flexibility, supporting the curation of literature graphs across any domain chosen by the user, whether high-level fields or specialized interdisciplinary areas. In addition to dataset curation, LitBench defines a comprehensive suite of literature tasks, ranging from node and edge level analyses to advanced applications such as related work generation. These tasks enable LLMs to internalize domain-specific knowledge and relationships embedded in the curated graph during training, while also supporting rigorous evaluation of model performance. Our results show that small domain-specific LLMs trained and evaluated on LitBench datasets achieve competitive performance compared to state-of-the-art models like GPT-4o and DeepSeek-R1. To enhance accessibility and ease of use, we open-source the tool along with an AI agent tool that streamlines data curation, model training, and evaluation.

With the advent of large language models (LLMs), managing scientific literature via LLMs has become a promising direction of research. However, existing approaches often overlook the rich structural and semantic relevance among scientific literature, limiting their ability to discern the relationships between pieces of scientific knowledge, and suffer from various types of hallucinations. These methods also focus narrowly on individual downstream tasks, limiting their applicability across use cases. We propose LitFM, the first literature foundation model designed for a wide variety of practical downstream tasks on domain-specific literature, with a focus on citation information. At its core, LitFM contains a novel graph retriever that can provide accurate and diverse recommendations for LLM to integrate graph structure information and relevant literature. LitFM also leverages a knowledge-infused LLM, fine-tuned through a well-developed instruction paradigm. It enables LitFM to extract domain-specific knowledge from literature and reason relationships among them. By integrating citation graphs during both training and inference, LitFM can generalize to unseen papers and accurately assess their relevance within existing literature. Additionally, we introduce new large-scale literature citation benchmark datasets on three academic fields, featuring sentence-level citation information and local context. Extensive experiments validate the superiority of LitFM, achieving 28.1% improvement on retrieval task in precision, and an average improvement of 7.52% over state-of-the-art across six downstream literature-related tasks.

The efficiency of Deep Learning (DL) training jobs is critically dependent on dataloaders, which facilitate the transfer of data from storage to DL-accelerated hardware during training. Recent advancements in data loading technology have demonstrated significant improvements, not only in reducing training times but also in introducing capabilities such as seamless integration with cloud storage. This paper examines the dataloader as a distinct component within the DL workflow, offering a detailed analysis of its structure and functionalities. We present a systematic evaluation of various dataloading libraries, investigating their performance across different configurations, including worker count, batch size, GPU scaling, data access patterns and remote loading. The evaluation highlights trade-offs in functionality, usability, and performance. Additionally, we examine the impact of dataset characteristics on data loading performance, showing that throughput decreases exponentially with image resolution. To support ongoing research and practical advancements, we introduce the first open-source benchmarking suite for DL data loading, which allows the community to replicate, extend, and build upon our experiments.

360-degree panoramic videos have gained considerable attention in recent years due to the rapid development of head-mounted displays (HMDs) and panoramic cameras. One major problem in streaming panoramic videos is that panoramic videos are much larger in size compared to traditional ones. Moreover, the user devices are often in a wireless environment, with limited battery, computation power, and bandwidth. To reduce resource consumption, researchers have proposed ways to predict the users’ viewports so that only part of the entire video needs to be transmitted from the server. However, the robustness of such prediction approaches has been overlooked in the literature: it is usually assumed that only a few models, pre-trained on past users’ experiences, are applied for prediction to all users. We observe that those pre-trained models can perform poorly for some users because they might have drastically different behaviors from the majority, and the pre-trained models cannot capture the features in unseen videos. In this work, we propose a novel meta learning based viewport prediction paradigm to alleviate the worst prediction performance and ensure the robustness of viewport prediction. This paradigm uses two machine learning models, where the first model predicts the viewing direction, and the second model predicts the minimum video prefetch size that can include the actual viewport. We first train two meta models so that they are sensitive to new training data, and then quickly adapt them to users while they are watching the videos. Evaluation results reveal that the meta models can adapt quickly to each user, and can significantly increase the prediction accuracy, especially for the worst-performing predictions.

Traffic forecasting can be highly challenging due to complex spatial-temporal correlations and non-linear traffic patterns. Existing works mostly model such spatial-temporal dependencies by considering spatial correlations and temporal correlations separately, or within a sliding temporal window, and fail to model the direct spatial-temporal correlations. Inspired by the recent success of transformers in the graph domain, in this paper, we propose to directly model the cross-spatial-temporal correlations on the adaptive spatial-temporal graph using local multi-head self-attentions. We then propose a novel Adaptive Graph Spatial-Temporal Transformer Network (ASTTN), which stacks multiple spatial-temporal attention layers to apply self-attention on the input graph, followed by linear layers for predictions. Experimental results on public traffic network datasets, METR-LA PEMS-BAY, PeMSD4, and PeMSD7, demonstrate the superior performance of our model.

In this paper we present NITOS Bikes Net, a framework for mobile sensing in a city-wide environment offering experimentation capabilities. More Specifically, we present a custom-made and modular prototype device that can be easily mounted on volunteers' bicycles dedicated to collecting environmental measurements and available WiFi networks. In addition, we present our enhancements in OMF framework through which we remotely control the operation of the developed devices, whenever they experience back-end connection. Finally, we analyze an indicative demonstration experiment which illustrates the capabilities of the developed framework.

In this paper we present the NITOS Bikes Net platform, a city-scale mobile sensing infrastructure that relies on bicycles of volunteer users. NITOS Bikes Net employs a custom-built embedded node that can be equipped with different types of sensors, and which can be easily mounted on a bicycle in order to opportunistically collect environmental and WiFi measurements in different parts of the city. Experimenters can remotely reserve and control the sensor nodes on bicycles as well as collect/visualize their measurements via the OMF/OML framework, which was extended in order to handle the intermittent connectivity and disconnected operation of the mobile nodes. We also provide a performance analysis of our node prototype in terms of sensing latency, end-to-end data transmission capability and power consumption, and report on a first experiment that was performed using NITOS Bikes Net in the city of Volos, Greece.