Hao Zhang

Causal Discovery Using Regression-Based Conditional Independence Tests

2017 · Proceedings of the AAAI Conference on Artificial Intelligence

Conditional independence (CI) testing is an important tool in causal discovery. Generally, by using CI tests, a set of Markov equivalence classes w.r.t. the observed data can be estimated by checking whether each pair of …

Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition

2019

We propose a new neural transfer method termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER). Specifically, two variants of DATNet, i.e., DATNet-F and DATNet-P, are investigated to explore effective feature …

The Recognition Method of Express Logistics Restricted Goods Based on Deep Convolution Neural Network

2020

With the continuous increase of China's express logistics business volume and the emergence of various security risks, social concern to the issue of express safety has been raised. Based on deep convolutional neural network, this …

Learning Environment Containerization of Machine Leaning for Cybersecurity

2020

Machine learning plays a critical role in detecting and preventing in the field of cybersecurity. However, many students have difficulties on configuring the appropriate coding environment and retrieving datasets on their own computers, which, to …

KG2Vec: A node2vec-based vectorization model for knowledge graph

2021 · PLoS ONE

Since the word2vec model was proposed, many researchers have vectorized the data in the research field based on it. In the field of social network, the Node2Vec model improved on the basis of word2vec can …

CLAIRE: Enabling Continual Learning for Real-time Autonomous Driving with a Dual-head Architecture

2022

Autonomous vehicles rely on a pre-trained object detector to perceive surroundings. However, when never seen before scenarios are encountered, late decisions may result in hard braking due to perceived threats. Image sequences leading to such …

Variational quantum circuit learning of entanglement purification in multiple degrees of freedom

2022 · arXiv (Cornell University)

Entanglement purification is a crucial technique for promising the effective entanglement channel in noisy large-scale quantum networks, yet complicated in designing protocols in multi-degree of freedom (DoF). To execute the above tasks easily and effectively, …

Principles and Practices of Real-Time Feature Computing Platforms for ML

2023 · Communications of the ACM

No abstract available.

A Survey on Aspect-Based Sentiment Quadruple Extraction with Implicit Aspects and Opinions

2023 · Research Square

<title>Abstract</title> Quadruple sentiment analysis is an essential task in aspect-based sentiment analysis that aims to understand people's viewpoints by analyzing four elements in text: category, aspect, opinion, and sentiment polarity. In recent years, quadruple sentiment …

Detecting Memory Errors in Python Native Code by Tracking Object Lifecycle with Reference Count

2023

Third-party Python modules are usually implemented as binary extensions by using native code (C/C++) to provide additional features and runtime acceleration. In native code, the heap-allocated PyObjects are managed by the reference counting mechanism provided …

Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly

2024 · arXiv (Cornell University)

Video anomaly understanding (VAU) aims to automatically comprehend unusual occurrences in videos, thereby enabling various applications such as traffic surveillance and industrial manufacturing. While existing VAU benchmarks primarily concentrate on anomaly detection and localization, our …

SelfBC: Self Behavior Cloning for Offline Reinforcement Learning

2024 · arXiv (Cornell University)

Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly conservative policies that resemble …

Meta-Prompt: Boosting Whisper's Performance in Low-Resource Speech Recognition

2024 · IEEE Signal Processing Letters

Recent advancements in large-scale pre-trained automatic speech recognition (ASR) foundation models (e.g., Whisper) have exhibited remarkable performance in speech processing tasks. A recently emerging paradigm, prompt tuning, offers a parameter-efficient approach for fine-tuning, which has …

Learning to generate and evaluate fact-checking explanations with transformers

2024 · Engineering Applications of Artificial Intelligence

In an era increasingly dominated by digital platforms, the spread of misinformation poses a significant challenge, highlighting the need for solutions capable of assessing information veracity. Our research contributes to the field of Explainable Artificial …

Preference Alignment Improves Language Model-Based TTS

2025

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust LMs to align with the preferences …

Privacy-Preserving Peer-to-Peer Cross-Domain Collaborative Filtering via Intent-Adaptive Graph Reconstruction

2026 · Electronics

Cross-domain collaborative filtering effectively alleviates the data sparsity issue but raises serious privacy concerns. Federated learning has been integrated into cross-domain collaborative filtering to reduce these risks by securely exchanging embeddings or model parameters. However, …

UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification

2018

The Fact Extraction and VERification (FEVER) shared task was launched to support the development of systems able to verify claims by extracting supporting or refuting facts from raw text. The shared task organizers provide a …

Efficient Memory Management for Large Language Model Serving with PagedAttention

2023

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and …