Author

Tao Zhong

Observed name: Zhong, Tao

Institutions: City University of Hong Kong, Chinese University of Hong Kong, Huawei Technologies (China)

Observed institutions: City University of Hong Kong, Chinese University of Hong Kong, Huawei Technologies (China), Wuhan University

ORCID: 0009-0003-5136-7769

Observed ORCID: 0009-0003-5136-7769

OpenAlex ID: A5125966016

Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-Of-Experts

2022 · Tao Zhong, Zhixiang Chi, et al. · neural information processing systems · 23

PDF

FedPAD: Aggregation-free federated learning with prototype-based adaptive distillation

2025 · Tao Zhong, Kaiyan Zhao, et al. · Knowledge-Based Systems · 2

LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation

2024 · Shu, Fangxun, Liao, Yue, et al. · arXiv (Cornell University) · 1

PDF

Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO

2026 · Ba, Yunpeng, Zheng, Zhi, et al. · arXiv (Cornell University)

PDF

EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

2026 · Kang, Qingcan, Liu, Mingyang, et al. · arXiv (Cornell University)

PDF

GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs

2026 · Luo, Yidong, Chen, Xuemin, et al. · arXiv (Cornell University)

PDF

Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction

2026 · Tsoi, Tristan, Deng, Jiajun, et al. · arXiv (Cornell University)

PDF

Towards Personalized Federated Learning for Dysarthric Speech Recognition

2026 · Zhong, Tao, Geng, Mengzhe, et al. · arXiv (Cornell University)

PDF

Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents

2026 · Kang, Qingcan, Mingyang, Liu, et al. · arXiv (Cornell University)

PDF

Automated Optimization Modeling via a Localizable Error-Driven Perspective

2026 · Liu, Weiting, Wu, Han, et al. · arXiv (Cornell University)

PDF

RIFT: Repurposing Negative Samples via Reward-Informed Fine-Tuning

2026 · Liu, Zehua, Liu, Shuqi, et al. · arXiv (Cornell University)

PDF

DHEvo: Data-Algorithm Based Heuristic Evolution for Generalizable MILP Solving

2026 · Zhihao Zhang, Siyuan Li, et al. · SSRN Electronic Journal

RIFT: Repurposing Negative Samples via Reward-Informed Fine-Tuning

2026 · Zehua Liu, Shuqi Liu, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

PDF

Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging

2025 · Wu, Han, Yao, Yuxuan, et al. · arXiv (Cornell University)

PDF

Works count: 16

Citation count: 26

H-index: 2

I10-index: 1