Chen Chen

HORNET

2015

We present HORNET, a system that enables high-speed end-to-end anonymous channels by leveraging next-generation network architectures. HORNET is designed as a low-latency onion routing system that operates at the network layer thus enabling a wide …

Chinese Common Noun Phrase Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers

2015 · Proceedings of the AAAI Conference on Artificial Intelligence

Pronoun resolution and common noun phrase resolution are the two most challenging subtasks of coreference resolution. While a lot of work has focused on pronoun resolution, common noun phrase resolution has almost always been tackled …

Informatization Exploration and Research for Medical Academics

2016 · DEStech Transactions on Engineering and Technology Research

Informatization which is a trend of the times, has overall rise in the field of medical education, and because of the characteristics of medical education, the informatization of medical academics has its particularity. This article …

A Scalable and Flexible Multi-User Semi-Quantum Secret Sharing

2018

In this letter, we proposed a novel scheme for the realization of scalable and flexible semi-quantum secret sharing between a boss and multiple dynamic agent groups. In our scheme, the boss Alice can not only …

Fast Modeling Methods for Complex System with Separable Features

2017

Data-driven modeling plays an increasingly important role in different areas of engineering. For most of existing methods, such as genetic programming (GP), the convergence speed might be too slow for large scale problems with a …

Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation

2020 · arXiv (Cornell University)

Few-shot semantic segmentation (FSS) has great potential for medical imaging applications. Most of the existing FSS techniques require abundant annotated semantic classes for training. However, these methods may not be applicable for medical images due …

Adversarial Self-Supervised Data-Free Distillation for Text Classification

2020 · arXiv (Cornell University)

Large pre-trained transformer-based language models have achieved impressive results on a wide range of NLP tasks. In the past few years, Knowledge Distillation(KD) has become a popular paradigm to compress a computationally expensive model to …

"Alexa, stop spying on me!"

2020

Voice assistants (VAs) are becoming highly popular recently as a general means of interacting with the Internet of Things. However, the use of always-on microphones on VAs imposes a looming threat on users' privacy. In …

Rethinking Reinforcement Learning based Logic Synthesis

2022 · arXiv (Cornell University)

Recently, reinforcement learning has been used to address logic synthesis by formulating the operator sequence optimization problem as a Markov decision process. However, through extensive experiments, we find out that the learned policy makes decisions …

SMpeaks: a semi-supervised clustering algorithm based on density peaks

2022 · 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022)

Clustering by fast search and find of Density Peaks (referred to as DP) was introduced by Alex Rodriguez and Alessandro Laio. DP algorithm is based on the idea that cluster centers are characterized by a …

FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs

2022 · arXiv (Cornell University)

Few-shot graph classification aims at predicting classes for graphs, given limited labeled graphs for each class. To tackle the bottleneck of label scarcity, recent works propose to incorporate few-shot learning frameworks for fast adaptations to …

Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting

2023 · arXiv (Cornell University)

Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust AGgregation …

Closed Iterative Correction Algorithm for Multi-target Dynamic Tracking and Positioning

2022

Aiming at the instability and low accuracy of Generalized Motion Simultaneous Localization and Mapping (GEM-SLAM), a closed iterative update dynamic tracking and location algorithm based on Generalized Labeled Multi-Bernoulli (GLMB) filter is proposed. It consists …

A Masked Attention Network with Query Sparsity Measurement for Time Series Anomaly Detection

2023

Time series aomaly detection has been widely studied in recent years. Previous research focuses on point-wise features and pairwise associations for feature learning or designed anomaly scores based on prior knowledge. However, these methods cannot …

Subgraph generation applied in GraphSAGE deal with imbalanced node classification

2023 · Research Square

Abstract In graph neural network applications,GraphSAGE applies inductive learning and has been widely applied in important research topics such as node classification.The subgraph of nodes directly affects the classification performance for GraphSAGE due to it …

Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR

2023 · IEEE/ACM Transactions on Audio Speech and Language Processing

Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as front-end to improve speech …

It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition

2024 · arXiv (Cornell University)

Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. Specifically, an LLM is utilized to carry …

Towards Multi-modal Transformers in Federated Learning

2024 · arXiv (Cornell University)

Multi-modal transformers mark significant progress in different domains, but siloed high-quality data hinders their further improvement. To remedy this, federated learning (FL) has emerged as a promising privacy-preserving paradigm for training models without direct access …

PQPU: A 4.4-<i>μ</i>J/Op 69.4-kOPS Agile Post-Quantum Crypto-Processor Across Multiple Mathematical Problems

2024 · IEEE Journal of Solid-State Circuits

Post-quantum cryptography (PQC) is currently being standardized to replace the existing public-key cryptography for data security in the era of quantum computing. PQC algorithms exhibit considerable diversity in their underlying mathematical problems, storage requirements, and …

PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have excelled in various tasks but are still vulnerable to jailbreaking attacks, where attackers create jailbreak prompts to mislead the model to produce harmful or offensive content. Current jailbreak methods either …

From 2D Document Interactions into Immersive Information Experience: An Example-Based Design by Augmenting Content, Spatializing Placement, Enriching Long-Term Interactions, and Simplifying Content Creations

2024 · arXiv (Cornell University)

Documents serve as a crucial and indispensable medium for everyday workplace tasks. However, understanding, interacting and creating such documents on today's planar interfaces without any intelligent support are challenging due to our natural cognitive constraints …

Research on Effectiveness Evaluation of Multi-UAV System Based on Improved Information Entropy by Prior Data

2025 · Unmanned Systems

Due to the characteristics of multiple random factors and flexible equipment composition, the effectiveness of multi-Unmanned Aerial Vehicle (UAV) system is difficult to evaluate accurately. Based on the modification of prior calculation data, an improved …

AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model

2025 · arXiv (Cornell University)

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in …

FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models

2025 · arXiv (Cornell University)

Bidirectional language models have better context understanding and perform better than unidirectional models on natural language understanding tasks, yet the theoretical reasons behind this advantage remain unclear. In this work, we investigate this disparity through …

Unifying Large Language Models and Knowledge Graphs: A Roadmap

2024 · IEEE Transactions on Knowledge and Data Engineering

Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs are black-box models, …