Get started
Author

Hai-Tao Zheng

Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking
2026 · Guo, Xinshuai, Wu, Junjie, et al. · arXiv (Cornell University)
PDF
Tool Retrievers Are Underestimated: Annotation Expansion Reveals True Capability
2026 · Zhu, Yanyu, Zhang, Chenheng, et al. · arXiv (Cornell University)
PDF
Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models
2026 · Zeng, Yongqin, Pan, Sicheng, et al. · arXiv (Cornell University)
PDF
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
2026 · Zhang, Yongheng, Liu, Ziang, et al. · arXiv (Cornell University)
PDF
CL$^2$GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction
2026 · Association for Computational Linguistics 2026, Kim, Hong-Gee, et al. · Underline Science Inc.
GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
2026 · Association for Computational Linguistics 2026, Bai, Lichen, et al. · Underline Science Inc.
Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
2026 · Association for Computational Linguistics 2026, Chen, Haibin, et al. · Underline Science Inc.
Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning
2026 · Zhu, Yanyu, Pao, Hoilam, et al. · arXiv (Cornell University)
PDF
Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction
2026 · Association for Artificial Intelligence 2026, Dong, Zhenhua, et al. · Underline Science Inc.
Works count: 9
Citation count:
H-index:
I10-index:
Year
Topic
Type