arXiv subjects

Andy Li

Publications and source records attributed to Andy Li.

10 recordsLinked to original sources

arXiv2026

Cooperative-ORCA*: Real-Time Proactive Deadlock Avoidance for Continuous-Space Multi-Agent Navigation

Multi-Agent Path Finding (MAPF) is a problem that requires computing collision-free paths for a set of agents from their start locations to designated goal locations. The problem has broad applications in domains where teams of robots must operate in a coordinated manner. ORCA* is a real time MAPF solver that assigns for each timestep a velocity for each agent. Due to its real time nature, it is myopic to future deadlocks that result from current decisions. ORCA*-MAPF attempts to remedy this limitation by introducing fallback mechanisms when deadlocks are detected. However, post hoc interventions often introduce significant flowtime overhead. In this paper, we introduce C-ORCA* and C-ORCA*-MAPF, continuous space MAPF algorithms that incorporate agents' entire spatial trajectory and their spatial dependencies to proactively prevent deadlocks from occurring, thus avoiding the high flowtime overhead associated with post hoc corrections in ORCA*-MAPF. The C-ORCA* family of algorithms significantly outperform previous state-of-the-art in terms of solve rate, runtime, and flowtime.

cs.RO↗

arXiv2026

HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers

Vision Transformers require significant computational resources and memory bandwidth, severely limiting their deployment on resource-constraint hardware. Most structured pruning methods reduce theoretical cost effectively, yet they typically operate at a single structural granularity and depend on multi-stage pipelines with importance ranking, auxiliary solvers or post-hoc magnitude thresholding, followed by a separate fine-tuning phase to recover accuracy. We propose Hierarchical Auto-Pruning (HiAP), which casts ViT pruning as a single budget-aware learning problem and jointly allocates sparsity across four granularities in one end-to-end phase. HiAP introduces stochastic Gumbel-Sigmoid gates at macro level (attention heads and FFN blocks) and micro level (intra-head dimensions and FFN neurons), and trains them against the task loss together with an analytical MAC cost term. The budget coefficient steers the network to a target compute level while the gates gradually harden into a dense, smaller sub-network at convergence. It does not require importance heuristics, ranking metrics, auxiliary solvers or secondary fine-tuning. On ImageNet, HiAP compresses DeiT-Base to 7.4G MACs at 80.88% top-1 and DeiT-Small to 3.1G at 79.33%, competitive with substantially more complex pipelines at matched compute. The structurally pruned network can be accelerated natively on stock kernels, and more than 90% of the theoretical MAC reduction is realized as measured throughput on an A100.

cs.CV↗

arXiv2025

From Framework to Practice: Designing a Real-World Telehealth Application for Palliative Care

As digital health solutions continue to reshape healthcare delivery, telehealth software applications have become vital for improving accessibility, continuity of care, and patient outcomes. This paper presents an analysis of designing a software application focused on Enhanced Telehealth Capabilities (ETHC) for palliative care, integrating across three socio-technical dimensions: quality, human values, and real-world. Designing for quality attributes -- such as performance, maintainability, safety, and security -- ensured that the system is technically robust and compliant with clinical standards. Designing for human values -- empathy, inclusivity, accessibility, and transparency -- helped enhance patient experience, trust, and ethical alignment. Designing for real-world -- through a multidisciplinary, experience-based co-design approach involving clinicians, patients, and carers that guided iterative cycles of prototyping, usability testing, and real-world evaluation -- ensured continuous refinement of features and alignment with clinical practice. The resulting telehealth software solution demonstrated that our socio-technical design framework was successful in producing a secure, equitable, and resilient digital health application. Our design approach can assist others designing software in health and other domains.

cs.HC↗

arXiv2025

Parallel Point-to-Point Shortest Paths and Batch Queries

We propose Orionet, efficient parallel implementations of Point-to-Point Shortest Paths (PPSP) queries using bidirectional search (BiDS) and other heuristics, with an additional focus on batch PPSP queries. We present a framework for parallel PPSP built on existing single-source shortest paths (SSSP) frameworks by incorporating pruning conditions. As a result, we develop efficient parallel PPSP algorithms based on early termination, bidirectional search, A$^*$ search, and bidirectional A$^*$ all with simple and efficient implementations. We extend our idea to batch PPSP queries, which are widely used in real-world scenarios. We first design a simple and flexible abstraction to represent the batch so PPSP can leverage the shared information of the batch. Orionet formalizes the batch as a query graph represented by edges between queried sources and targets. In this way, we directly extended our PPSP framework to batched queries in a simple and efficient way. We evaluate Orionet on both single and batch PPSP queries using various graph types and distance percentiles of queried pairs, and compare it against two baselines, GraphIt and MBQ. Both of them support parallel single PPSP and A$^*$ using unidirectional search. On 14 graphs we tested, on average, our bidirectional search is 2.9$\times$ faster than GraphIt, and 6.8$\times$ faster than MBQ. Our bidirectional A$^*$ is 4.4$\times$ and 6.2$\times$ faster than the A$^*$ in GraphIt and MBQ, respectively. For batched PPSP queries, we also provide in-depth experimental evaluation, and show that Orionet provides strong performance compared to the plain solutions.

cs.DC↗

arXiv2025

Enhancing Strawberry Yield Forecasting with Backcasted IoT Sensor Data and Machine Learning

Rapid global population growth underscores the need for digitally enabled agricultural systems that support sustainable food production and data-driven resource management for farmers and stakeholders. The adoption of Internet of Things (IoT) technologies, capable of capturing real-time environmental (e.g., temperature, humidity) and operational (e.g., irrigation) parameters, is a crucial step toward enabling advanced applications such as AI-based yield forecasting. However, the effectiveness of such models is often constrained by limited data availability, particularly in dynamic farm environments where IoT observations must be accumulated over multiple growing seasons. In this study, we deployed IoT sensors in strawberry production polytunnels over two growing seasons to collect data on water usage, internal and external temperature and humidity, soil moisture, soil temperature, and photosynthetically active radiation. These observations were combined with manually recorded yield data spanning four seasons. To address gaps in IoT data for the two seasons without sensor coverage, we developed an AI-based backcasting approach that synthesizes missing sensor observations using historical weather data from a nearby station and existing polytunnel measurements. We then trained AI-based yield forecasting models using both real and synthetic datasets. In this retrospective evaluation, results show that incorporating synthetic data improved yield forecasting accuracy, with models trained on the combined dataset outperforming those using only real sensor, weather, and yield data.

cs.LG↗

arXiv2025

Comparing Large Language Models and Traditional Machine Translation Tools for Translating Medical Consultation Summaries: A Pilot Study

This study evaluates how well large language models (LLMs) and traditional machine translation (MT) tools translate medical consultation summaries from English into Arabic, Chinese, and Vietnamese. It assesses both patient, friendly and clinician, focused texts using standard automated metrics. Results showed that traditional MT tools generally performed better, especially for complex texts, while LLMs showed promise, particularly in Vietnamese and Chinese, when translating simpler summaries. Arabic translations improved with complexity due to the language's morphology. Overall, while LLMs offer contextual flexibility, they remain inconsistent, and current evaluation metrics fail to capture clinical relevance. The study highlights the need for domain-specific training, improved evaluation methods, and human oversight in medical translation.

cs.CL↗

arXiv2025

CBS with Continuous-Time Revisit

Multi-Agent Path Finding in Continuous Time (\mapfr) extends the classical MAPF problem by allowing agents to operate in continuous time. Conflict-Based Search with Continuous Time (CCBS) is a foundational algorithm for solving \mapfr optimally. In this paper, we revisit the theoretical claims of CCBS and show the algorithm is incomplete, due to an uncountably infinite state space created by continuous wait durations. Through theoretical analysis and counter-examples, we examine the inherent challenges of extending existing MAPF solvers to address \mapfr while preserving optimality guarantees. By restricting waiting duration to fixed amounts, we identify a related sub-problem on graphs, \mapfrdt which we show is optimally solvable, including by CCBS. It remains an open question whether similar models exist for \mapfrct, a generalised version of \mapfrdt that allows arbitrary wait times, and \mapfrcs, which further allows arbitrary movements in continuous space.

cs.MA↗

arXiv2024

Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning

Pruning of deep neural networks has been an effective technique for reducing model size while preserving most of the performance of dense networks, crucial for deploying models on memory and power-constrained devices. While recent sparse learning methods have shown promising performance up to moderate sparsity levels such as 95% and 98%, accuracy quickly deteriorates when pushing sparsities to extreme levels due to unique challenges such as fragile gradient flow. In this work, we explore network performance beyond the commonly studied sparsities, and develop techniques that encourage stable training without accuracy collapse even at extreme sparsities, including 99.90%, 99.95\% and 99.99% on ResNet architectures. We propose three complementary techniques that enhance sparse training through different mechanisms: 1) Dynamic ReLU phasing, where DyReLU initially allows for richer parameter exploration before being gradually replaced by standard ReLU, 2) weight sharing which reuses parameters within a residual layer while maintaining the same number of learnable parameters, and 3) cyclic sparsity, where both sparsity levels and sparsity patterns evolve dynamically throughout training to better encourage parameter exploration. We evaluate our method, which we term Extreme Adaptive Sparse Training (EAST) at extreme sparsities using ResNet-34 and ResNet-50 on CIFAR-10, CIFAR-100, and ImageNet, achieving competitive or improved performance compared to existing methods, with notable gains at extreme sparsity levels.

cs.CV↗

arXiv2023

Mini-Giants: "Small" Language Models and Open Source Win-Win

ChatGPT is phenomenal. However, it is prohibitively expensive to train and refine such giant models. Fortunately, small language models are flourishing and becoming more and more competent. We call them "mini-giants". We argue that open source community like Kaggle and mini-giants will win-win in many ways, technically, ethically and socially. In this article, we present a brief yet rich background, discuss how to attain small language models, present a comparative study of small language models and a brief discussion of evaluation methods, discuss the application scenarios where small language models are most needed in the real world, and conclude with discussion and outlook.

cs.CL↗

arXiv2023

Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing

Federated Learning (FL) presents a decentralized approach to model training in the agri-food sector and offers the potential for improved machine learning performance, while ensuring the safety and privacy of individual farms or data silos. However, the conventional FL approach has two major limitations. First, the heterogeneous data on individual silos can cause the global model to perform well for some clients but not all, as the update direction on some clients may hinder others after they are aggregated. Second, it is lacking with respect to the efficiency perspective concerning communication costs during FL and large model sizes. This paper proposes a new technical solution that utilizes network pruning on client models and aggregates the pruned models. This method enables local models to be tailored to their respective data distribution and mitigate the data heterogeneity present in agri-food data. Moreover, it allows for more compact models that consume less data during transmission. We experiment with a soybean yield forecasting dataset and find that this approach can improve inference performance by 15.5% to 20% compared to FedAvg, while reducing local model sizes by up to 84% and the data volume communicated between the clients and the server by 57.1% to 64.7%.

cs.LG↗