Get started
Author

Wei Lin

Toward intellidynamics: A path from HH2 to modern AI
2026 · Wei Lin, Jianshe Yu · Discrete and Continuous Dynamical Systems - I Intelligence · 2
PDF
Tool Retrievers Are Underestimated: Annotation Expansion Reveals True Capability
2026 · Zhu, Yanyu, Zhang, Chenheng, et al. · arXiv (Cornell University)
PDF
One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control
2026 · Lin, Zihan, Wang, Xiaohan, et al. · arXiv (Cornell University)
PDF
When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents
2026 · Lin, Zihan, Chen, Zhenyu, et al. · arXiv (Cornell University)
PDF
HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning
2026 · Guo, Yucan, Wang, Xiaohan, et al. · arXiv (Cornell University)
PDF
Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning
2026 · Wang, Li, Lu, Xiaodong, et al. · arXiv (Cornell University)
PDF
Unpaired Modality-Agnostic Generative Recommendation
2026 · Shen, Weihao, Chen, Wei, et al. · arXiv (Cornell University)
PDF
Requirement--Evidence Alignment for Compositional E-Commerce Queries
2026 · Shen, Weihao, Chen, Wei, et al. · arXiv (Cornell University)
PDF
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
2026 · Shan, Yingyu, Guo, Yuhang, et al. · arXiv (Cornell University)
PDF
When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
2026 · Wang, Li, Lu, Xiaodong, et al. · arXiv (Cornell University)
PDF
Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
2026 · Wang, Li, Wang, Xiaohan, et al. · arXiv (Cornell University)
PDF
AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment
2026 · Wei, Zhenlin, Jian, Pu, et al. · arXiv (Cornell University)
PDF
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
2026 · Lin, Zihan, Wang, Xiaohan, et al. · arXiv (Cornell University)
PDF
SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning
2026 · Wang, Xuan, Ming, Yu, et al. · arXiv (Cornell University)
PDF
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
2026 · Sun, Jingbo, Chong, Wenyue, et al. · arXiv (Cornell University)
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
2026 · Sun, Jingbo, Chong, Wenyue, et al. · arXiv (Cornell University)
PDF
$π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
2026 · Zhang, Yaocheng, Zhu, Yuanheng, et al. · arXiv (Cornell University)
PDF
SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training
2026 · Zhang, Qi, Wang, Yifei, et al. · arXiv (Cornell University)
PDF
Works count: 18
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type