Mingyi Hong

AutoScaffold: AI-Guided Scaffolding for Reinforcement Learning of Language Models

Zijian Zhang, Rizhen Hu, Jiangweizhi Peng, et al.

MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control

Athanasios Glentis, Dawei Li, Mingyi Hong

SparseDitto: Customizing GPU Kernels for Different Sparsity Patterns with LLM-Based Agentic System

Shiyang Li, Guangyan Sun, Jinwei Tang, et al.

Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$

Dawei Li, Xiaotian Jiang, Mingyi Hong

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

Zijian Zhang, Rizhen Hu, Athanasios Glentis, et al.

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science

An Luo, Jin Du, Xun Xian, et al.

AgentDS is a benchmark that tests how well AI agents and humans working together can solve real-world data science problems across industries like healthcare, retail, and manufacturing. The research found that while AI agents alone perform poorly on these domain-specific tasks, human-AI collaboration produces the best results, showing that human expertise remains crucial even as AI becomes more advanced.