wovepaper — the arXiv observatory

papers

Publications (17)

Testing degree heterogeneity in directed networks

Lu Pan, Qiuping Wang, Ting Yan

How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization

Yangyi Fang, Jiaye Lin, Xiaoliang Fu +6

Generating Pertinent and Diversified Comments with Topic-aware Pointer-Generator Networks

Junheng Huang, Lu Pan, Kang Xu +2

From $lo g I ¨ $ to $I ¨ $ : Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight

Xiaoliang Fu, Jiaye Lin, Yangyi Fang +6

Differentially private estimation in a class of directed network models

Lu Pan, Jianwei Hu, Peiyan Li

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training

Zhongyu He, Yuanfan Li, Fei Huang +9

Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems

Xuxin Cheng, Ke Zeng, Zhiquan Cao +65

Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning

Chishui Chen, Jiaye Lin, Te Sun +6

Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation

Chishui Chen, Yaoyou Fan, Te Sun +11

astro-ph.EP2020

Inverted Channel Belts and Floodplain Clays to the East of Tempe Terra, Mars: Implications for Persistent Fluvial Activity on Early Mars

Zhenghao Liu, Yang Liu, Lu Pan +4

Moment estimation in paired comparison models with a growing number of subjects

Qiuping Wang, Lu Pan, Ting Yan

Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Model

Sheng Bi, Xiya Cheng, Yuan-Fang Li +5

MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning

Xiaoliang Fu, Jiaye Lin, Yangyi Fang +7

astro-ph.EP2022

Martian meteorites reflectance and implications for rover missions

Lucia Mandon, Pierre Beck, Cathy Quantin-Nataf +7

Single Document Image Highlight Removal via A Large-Scale Real-World Dataset and A Location-Aware Network

Lu Pan, Yu-Hsuan Huang, Hongxia Xie +4

ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments

Lu Pan, Hongwei Zhao

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

Jingwen Chen, Wenkai Yang, Shengda Fan +7