Wei Wu

An Optimized Algorithm in Risk Calculating

2016

CORAS is an EU funded project which developing a methodology and a tool that supported framework for model-based risk assessment targeting security critical systems. According to the subjectivity of risk computation in CORAS's application, meta-risk …

Glyce: Glyph-vectors for Chinese Character Representations

2019 · arXiv (Cornell University)

It is intuitive that NLP tasks for logographic languages like Chinese should benefit from the use of the glyph information in those languages. However, due to the lack of rich pictographic evidence in glyphs and …

Neural Response Generation with Meta-words

2019

We present open domain response generation with meta-words. A meta-word is a structured record that describes various attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues …

Memory access integrity: detecting fine-grained memory access errors in binary code

2019 · Cybersecurity

As one of the most notorious programming errors, memory access errors still hurt modern software security. Particularly, they are hidden deeply in important software systems written in memory unsafe languages like C/C++. Plenty of work …

Public Cloud Security Protection Research

2019

With the rapid development of cloud computing, public cloud as the main form, the attack value is higher, and security is more difficult. This paper expounds the background and concept of public cloud. Starting from …

Wave–Particle–Entanglement–Ignorance Complementarity for General Bipartite Systems

2020 · Entropy

Wave-particle duality as the defining characteristic of quantum objects is a typical example of the principle of complementarity. The wave-particle-entanglement (WPE) complementarity, initially developed for two-qubit systems, is an extended form of complementarity that combines …

Fast laser cooling using optimal quantum control

2021 · Physical Review A

Cooling down a trapped ion into its motional ground state is a central step for trapped-ion-based quantum information processing. State-of-the-art cooling schemes often work under a set of optimal cooling conditions derived analytically using a …

TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization

2022 · arXiv (Cornell University)

Although pre-trained language models (PLMs) have achieved great success and become a milestone in NLP, abstractive conversational summarization remains a challenging but less studied task. The difficulty lies in two aspects. One is the lack …

A Lattice-Based Redactable Signature Scheme using Cryptographic Accumulators for Trees

2022 · The Computer Journal

Abstract Redactable signatures allow the signature holder to remove admissible data blocks in the signed data while generating valid signatures about different redacted data without communicating with the primary signer. Now, this sort of signature …

Popularity Bias is not Always Evil: Disentangling Benign and Harmful Bias for Recommendation

2022 · IEEE Transactions on Knowledge and Data Engineering

Recommender system usually suffers from severepopularity bias— the collected interaction data usually exhibits quite imbalanced or even long-tailed distribution over items. Such skewed distribution may result from the users’conformityto the group, which deviates from reflecting …

RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank

2023 · arXiv (Cornell University)

Unsupervised sentence representation learning is one of the fundamental problems in natural language processing with various downstream applications. Recently, contrastive learning has been widely adopted which derives high-quality sentence representations by pulling similar semantics closer …

XPrompt: Exploring the Extreme of Prompt Tuning

2022

Prompt tuning learns soft prompts to condition the frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner. While prompt tuning has gradually reached the performance level of fine-tuning as the model …

A Blockchain‐Based Trustworthy Access Control Scheme for Medical Data Sharing

2024 · IET Information Security

Blockchain is commonly employed in access control to provide safe medical data exchange because of the characteristics of decentralization, nontamperability, and traceability. Patients share personal health data by granting access rights to users or medical …

2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models

2024 · arXiv (Cornell University)

Tables are ubiquitous across various domains for concisely representing structured information. Empowering large language models (LLMs) to reason over tabular data represents an actively explored direction. However, since typical LLMs only support one-dimensional~(1D) inputs, existing …

KA2SE: Key-Aggregation Authorized Searchable Encryption Scheme for Data Sharing in Wireless Sensor Networks

2024 · IEEE Transactions on Services Computing

As a promising technology, key-aggregation searchable encryption with constant computation overhead is especially suitable for sensor nodes with limited computation resources in wireless sensor networks. However, in most of the existing key-aggregation searchable encryption schemes, …

Enhancing Few-Shot Image Classification With a Multi-Faceted Self-Supervised and Contrastive Learning Approach

2024 · IEEE Access

One effective approach for solving few-shot classification is learning deep representations that measure the similarity between query images and a few support images of specific categories. Recent methods overly relied on a single metric, resulting …

Low-Rank Algorithms for Ab Initio Valence Bond Approaches

2025 · Journal of Chemical Theory and Computation

Valence bond (VB) theory is an ab initio approach that provides intuitive pictures and insights into chemical bonds and reaction mechanisms. This work integrates low-rank algorithms, including the resolution of the identity and the chain …

Research on Text Sentiment Recognition Algorithm Integrated Enneagram and BiGRU-attention-CNN

2025

This study introduces a novel text sentiment analysis model that incorporates the enneagram personality theory into deep learning methodologies to address the oversight of traditional sentiment analysis tasks regarding the influence of individual personality traits …

A Semi-Supervised Learning Framework for Encrypted Traffic Classification Based on Supervised Contrastive Learning and Masked Sequence Prediction Tasks

2025

With the widespread adoption of encryption technologies, the proportion of encrypted traffic in network traffic has significantly increased, making encrypted traffic classification a key technology for enhancing network security and optimizing network performance. Although existing …

Estimation of photovoltaic power generation in traditional protected villages in mountainous areas based on satellite image semantic segmentation and 3D terrain reconstruction

2025 · Journal of Asian Architecture and Building Engineering

With the growing demand for renewable energy, rooftop PV systems have gained widespread attention and adoption. However, existing methods for assessing PV potential are designed for urban areas and cannot address traditional protected villages or …

Hierarchical Recurrent Attention Network for Response Generation

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

We study multi-turn response generation in chatbots where a response is generated according to a conversation context. Existing work has modeled the hierarchy of the context, but does not pay enough attention to the fact …

Neural Response Generation With Dynamic Vocabularies

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

We study response generation for open domain conversation in chatbots. Existing methods assume that words in responses are generated from an identical vocabulary regardless of their inputs, which not only makes them vulnerable to generic …

Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots

2017

We study response selection for multiturn conversation in retrieval-based chatbots. Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships among utterances or …

Multi-Representation Fusion Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

2019

We consider context-response matching with multiple types of representations for multi-turn response selection in retrieval-based chatbots. The representations encode semantics of contexts and responses on words, n-grams, and sub-sequences of utterances, and capture both short-term …

One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues

2019

Currently, researchers have paid great attention to retrieval-based dialogues in opendomain. In particular, people study the problem by investigating context-response matching for multi-turn response selection based on publicly recognized benchmark data sets. State-of-the-art methods require …

Low-Resource Knowledge-Grounded Dialogue Generation

2020 · arXiv (Cornell University)

Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are difficult to obtain. Motivated by the …

CorefQA: Coreference Resolution as Query-based Span Prediction

2020

In this paper, we present CorefQA, an accurate and extensible approach for the coreference resolution task. We formulate the problem as a span prediction task, like in question answering: A query is generated for each …

Knowledge-Grounded Dialogue Generation with Pre-trained Language Models

2020

We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pretrained language model with a knowledge selection module, and …

ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

2021

Yuanmeng Yan, Rumei Li, Sirui Wang, Fuzheng Zhang, Wei Wu, Weiran Xu. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume …