Yue Huang

A course-oriented book recommendation method based on library classification ontology

2016

With the advent of Massive Open Online Course, or MOOC, academic librarians have already begun to participate in all aspects of MOOC. During the resource construction of a self-built MOOC platform, one issue that the …

Unsupervised Adversarial Graph Alignment with Graph Embedding

2019 · arXiv (Cornell University)

Graph alignment, also known as network alignment, is a fundamental task in social network analysis. Many recent works have relied on partially labeled cross-graph node correspondences, i.e., anchor links. However, due to the privacy and …

Harmonizing Transferability and Discriminability for Adapting Object Detectors

2020 · arXiv (Cornell University)

Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline. Whilst adversarial adaptation significantly enhances the transferability of feature representations, …

Hard Class Rectification for Domain Adaptation

2020 · arXiv (Cornell University)

Domain adaptation (DA) aims to transfer knowledge from a label-rich and related domain (source domain) to a label-scare domain (target domain). Pseudo-labeling has recently been widely explored and used in DA. However, this line of …

1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in different languages, presenting challenges for …

Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification

2024 · arXiv (Cornell University)

Generalizable vehicle re-identification (ReID) seeks to develop models that can adapt to unknown target domains without the need for additional fine-tuning or retraining. Previous works have mainly focused on extracting domain-invariant features by aligning data …

Current Situation of Students Using AI Tools to Assist English Learning -- A Case Study of Guangdong University of Education

2024 · Lecture Notes in Education Psychology and Public Media

The use of Artificial Intelligence (AI) tools to assist English learning has increasingly become a trend in recent years. These AI-generating tools are favored by college students for their speed, wide range, and small spatial …

Better Datasets Start From RefineLab: Automatic Optimization for High-Quality Dataset Refinement

2025 · arXiv (Cornell University)

High-quality Question-Answer (QA) datasets are foundational for reliable Large Language Model (LLM) evaluation, yet even expert-crafted datasets exhibit persistent gaps in domain coverage, misaligned difficulty distributions, and factual inconsistencies. The recent surge in generative model-powered …

Decompose and Attribute: Boosting Generalizable Open-Set Object Detection via Objectness Score

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Open-set object detection (OSOD) aims to recognize known object categories while localizing previously unseen instances. However, real-world scenarios often involve co-occurring domain shifts and novel object categories. Existing OSOD methods typically overlook domain shifts, relying …

TASE: Token Awareness and Structured Evaluation for Multilingual Language Models

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

While large language models (LLMs) have demonstrated remarkable performance on high-level semantic tasks, they often struggle with fine-grained, token-level understanding and structural reasoning—capabilities that are essential for applications requiring precision and control. We introduce TASE, …