Xin Jin

Distilling Deep Neural Networks for Robust Classification with Soft Decision Trees

2018

Recent deep neural networks have achieved impressive performance in image classification. However, these networks are sensitive to the attack of adversarial examples, leading to a sharp drop in accuracy. To address this issue, this paper …

Software Defect Prediction Model Based on Improved Deep Forest and AutoEncoder by Forest

2019 · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering

Software defect prediction is an important way to make full use of software test resources and improve software performance. To deal with the problem that of the shallow machine learning based software defect prediction model …

Defending Against Adversarial Examples via Soft Decision Trees Embedding

2019

Convolutional neural networks (CNNs) have shown vulnerable to adversarial examples which contain imperceptible perturbations. In this paper, we propose an approach to defend against adversarial examples with soft decision trees embedding. Firstly, we extract the …

Flash

2019

Offchain networks emerge as a promising solution to address the scalability challenge of blockchain. Participants make payments through offchain networks instead of committing transactions on-chain. Routing is critical to the performance of offchain networks. Existing …

FaaSLight: General Application-Level Cold-Start Latency Optimization for Function-as-a-Service in Serverless Computing

2022 · arXiv (Cornell University)

Serverless computing is a popular cloud computing paradigm that frees developers from server management. Function-as-a-Service (FaaS) is the most popular implementation of serverless computing, representing applications as event-driven and stateless functions. However, existing studies report …

FLASH: Heterogeneity-Aware Federated Learning at Scale

2022 · IEEE Transactions on Mobile Computing

Federated learning (FL) becomes a promising machine learning paradigm. The impact of heterogeneous hardware specifications and dynamic states on the FL process has not yet been studied systematically. This paper presents the first large-scale study …

Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning

2023 · arXiv (Cornell University)

Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected future rewards. Recent work has attempted to alleviate the overestimation bias …

Optimizing RLHF Training for Large Language Models with Stage Fusion

2024 · arXiv (Cornell University)

We present RLHFuse, an efficient training system with stage fusion for Reinforcement Learning from Human Feedback (RLHF). Due to the intrinsic nature of RLHF training, i.e., the data skewness in the generation stage and the …

LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism

2024

The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between different requests as well as between different phases of the same request. Restricted by static …

Rethinking Domain Adaptation and Generalization in the Era of CLIP

2024 · arXiv (Cornell University)

In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain. Recently, the large vision-language pre-trained model, i.e., CLIP has …

Stochastic noise can be helpful for variational quantum algorithms

2025 · Physical Review A

Saddle points constitute a crucial challenge for first-order gradient descent algorithms. In notions of classical machine learning, they are avoided, for example, by means of stochastic gradient descent methods. In this work, we provide evidence …

World Models and World Action Models (WAM): From Foundation Simulators to Embodied Action

2026 · Zenodo (CERN European Organization for Nuclear Research)

World models—internal predictive representations that enable agents to simulate future states, anticipate consequences, and plan actions—have emerged as a foundational paradigm in embodied artificial intelligence. Originating from model-based reinforcement learning, this field has undergone a …

Knowledge-driven adaptive alignment method for reflective optical systems based on physics-informed multi-task learning

2026 · Optics Express

The precision of optical mirror alignment is fundamental to ensuring optical system performance. However, traditional manual alignment is limited by its heavy reliance on expert experience, while existing data-driven approaches are constrained by their demand …

Systems-Level Support for Hybrid Quantum-Classical Learning: A Systematic Review with a Medical Imaging Translation Lens

2026 · Journal of Imaging

Hybrid quantum-classical learning pipelines combine conventional accelerators, quantum runtimes, and quantum processing units (QPUs), creating scheduling, memory, isolation, encoding, and deployment challenges that are not captured by application-level quantum machine learning surveys alone. This paper …

Improve word embedding using both writing and pronunciation

2018 · PLoS ONE

Text representation can map text into a vector space for subsequent use in numerical calculations and processing tasks. Word embedding is an important component of text representation. Most existing word embedding models focus on writing …