Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xingyu Lu

Xingyu Lu

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×3ML×1Vision×1NLP×1Multimedia×1

Frequent co-authors

Kun Feng1×
Ziwei Shan1×
Yuchen Fang1×
Yiyang Tan1×
Sihan Lu1×
Shuqi Gu1×

Research Timeline

2026
VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multimodal models.

KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning

KairosAgent is a novel agentic framework that combines Large Language Models (LLMs) for semantic reasoning and Time Series Foundation Models (TSFMs) for numerical forecasting, achieving superior multimodal time series prediction.

OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation

OptSkills introduces an archetype-centric skill learning agent that improves the generalization of solving optimization problems from natural language by clustering problems by underlying archetypes and distilling reusable workflow skills.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 28, 2026

KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning

Kun Feng, Ziwei Shan, Yuchen Fang, Yiyang Tan +5 more

KairosAgent is a novel agentic framework that combines Large Language Models (LLMs) for semantic reasoning and Time Series Foundation Models (TSFMs) for numerical forecasting, achieving superior multi…

View →
cs.AIcs.LGRecentMay 28, 2026

OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation

Haochen Yang, Ke Zhao, Mengyuan Ma, Xingyu Lu +2 more

OptSkills introduces an archetype-centric skill learning agent that improves the generalization of solving optimization problems from natural language by clustering problems by underlying archetypes a…

View →
cs.CVcs.AIcs.CLRecentMay 27, 2026

VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning

Xingyu Lu, Jinpeng Wang, Yi-Fan Zhang, Yankai Yang +12 more

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multim…

View →