Yu Jiang

Mingzhuang Hua, Francisco Camara Pereira, Yu Jiang et al.

The urban transportation system is a combination of multiple transport modes, and the interdependencies across those modes exist. This means that the travel demand across different travel modes could be correlated as one mode may receive demand from or create demand for another mode, not to mention natural correlations between different demand time series due to general demand flow patterns across the network. It is expectable that cross-modal ripple effects become more prevalent, with Mobility as a Service. Therefore, by propagating demand data across modes, a better demand prediction could be obtained. To this end, this study explores various machine learning models and transfer learning strategies for cross-modal demand prediction. The trip data of bike-share, metro, and taxi are processed as the station-level passenger flows, and then the proposed prediction method is tested in the large-scale case studies of Nanjing and Chicago. The results suggest that prediction models with transfer learning perform better than unimodal prediction models. Furthermore, stacked Long Short-Term Memory model performs particularly well in cross-modal demand prediction. These results verify our combined method's forecasting improvement over existing benchmarks and demonstrate the good transferability for cross-modal demand prediction in multiple cities.

Yinsicheng Jiang, Yeqi Huang, Liang Cheng et al.

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with retrieved context but often suffers from downgraded prefill performance as modern applications demand longer and more complex inputs. Existing caching techniques either preserve accuracy with low cache reuse or improve reuse at the cost of degraded reasoning quality. We present RAGBoost, an efficient RAG system that achieves high cache reuse without sacrificing accuracy through accuracy-preserving context reuse. RAGBoost detects overlapping retrieved items across concurrent sessions and multi-turn interactions, using efficient context indexing, ordering, and de-duplication to maximize reuse, while lightweight contextual hints maintain reasoning fidelity. It integrates seamlessly with existing LLM inference engines and improves their prefill performance by 1.5-3X over state-of-the-art methods, while preserving or even enhancing reasoning accuracy across diverse RAG and agentic AI workloads. Our code is released at: https://github.com/Edinburgh-AgenticAI/RAGBoost.

Yinsicheng Jiang, Yao Fu, Yeqi Huang et al.

The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory resources. These factors jointly affect system Cost, Accuracy, and Performance (CAP), making trade-offs inevitable. Existing benchmarks often fail to capture these trade-offs accurately, complicating practical deployment decisions. To address this, we introduce MoE-CAP, a benchmark specifically designed for MoE systems. Our analysis reveals that achieving an optimal balance across CAP is difficult with current hardware; MoE systems typically optimize two of the three dimensions at the expense of the third-a dynamic we term the MoE-CAP trade-off. To visualize this, we propose the CAP Radar Diagram. We further introduce sparsity-aware performance metrics-Sparse Memory Bandwidth Utilization (S-MBU) and Sparse Model FLOPS Utilization (S-MFU)-to enable accurate performance benchmarking of MoE systems across diverse hardware platforms and deployment scenarios.

Inon Peled, Kelvin Lee, Yu Jiang et al.

As Public Transport (PT) becomes more dynamic and demand-responsive, it increasingly depends on predictions of transport demand. But how accurate need such predictions be for effective PT operation? We address this question through an experimental case study of PT trips in Metropolitan Copenhagen, Denmark, which we conduct independently of any specific prediction models. First, we simulate errors in demand prediction through unbiased noise distributions that vary considerably in shape. Using the noisy predictions, we then simulate and optimize demand-responsive PT fleets via a linear programming formulation and measure their performance. Our results suggest that the optimized performance is mainly affected by the skew of the noise distribution and the presence of infrequently large prediction errors. In particular, the optimized performance can improve under non-Gaussian vs. Gaussian noise. We also find that dynamic routing could reduce trip time by at least 23% vs. static routing. This reduction is estimated at 809,000 EUR/year in terms of Value of Travel Time Savings for the case study.

Inon Peled, Kelvin Lee, Yu Jiang et al.

This study develops an online predictive optimization framework for dynamically operating a transit service in an area of crowd movements. The proposed framework integrates demand prediction and supply optimization to periodically redesign the service routes based on recently observed demand. To predict demand for the service, we use Quantile Regression to estimate the marginal distribution of movement counts between each pair of serviced locations. The framework then combines these marginals into a joint demand distribution by constructing a Gaussian copula, which captures the structure of correlation between the marginals. For supply optimization, we devise a linear programming model, which simultaneously determines the route structure and the service frequency according to the predicted demand. Importantly, our framework both preserves the uncertainty structure of future demand and leverages this for robust route optimization, while keeping both components decoupled. We evaluate our framework using a real-world case study of autonomous mobility in a university campus in Denmark. The results show that our framework often obtains the ground truth optimal solution, and can outperform conventional methods for route optimization, which do not leverage full predictive distributions.