activity
20162025
most citedYour Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination

41 citations · 173 across the 41 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

GeoRef: Referring Expressions in Geometry via Task Formulation, Synthetic Supervision, and Reinforced MLLM-based Solutions

Bing Liu, Wenqiang Yv, Xuzheng Yang +6

AI-driven geometric problem solving is a complex vision-language task that requires accurate diagram interpretation, mathematical reasoning, and robust cross-modal grounding. A fou…

cs.LG2024

Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach

Hanyang Yuan, Jiarong Xu, Renhong Huang +3

Graph neural networks (GNNs) have attracted considerable attention due to their diverse applications. However, the scarcity and quality limitations of graph data present challenges…

cs.LG2024

Complementary Fusion of Deep Network and Tree Model for ETA Prediction

YuRui Huang, Jie Zhang, HengDa Bao +2

Estimated time of arrival (ETA) is a very important factor in the transportation system. It has attracted increasing attentions and has been widely used as a basic service in navig…

cs.LG20242 cited

Are Synthetic Time-series Data Really not as Good as Real Data?

Fanzhe Fu, Junru Chen, Jing Zhang +3

Time-series data presents limitations stemming from data quality issues, bias and vulnerabilities, and generalization problem. Integrating universal data synthesis methods holds pr…

cs.LG202410 cited

Robust Semi-Supervised Learning for Self-learning Open-World Classes

Wenjuan Xi, Xin Song, Weili Guo +1

Existing semi-supervised learning (SSL) methods assume that labeled and unlabeled data share the same class space. However, in real-world applications, unlabeled data always contai…

cs.LG20232 cited

When to Pre-Train Graph Neural Networks? From Data Generation Perspective!

Yuxuan Cao, Jiarong Xu, Carl Yang +5

In recent years, graph pre-training has gained significant attention, focusing on acquiring transferable knowledge from unlabeled graph data to improve downstream performance. Desp…