collaborators

6 papers

cs.LG2026

How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining

Kairong Luo, Zhenbo Sun, Haodong Wen +5

Due to the scarcity of high-quality data, large language models (LLMs) are often trained on mixtures of data with varying quality levels, even after sophisticated data curation. A…

cs.LG2026

Larger Datasets Can Be Repeated More: A Theoretical Analysis of Multi-Epoch Scaling in Linear Regression

Tingkai Yan, Haodong Wen, Binghui Li +3

While data scaling laws of large language models (LLMs) have been widely examined in the one-pass regime with massive corpora, their form under limited data and repeated epochs rem…

cs.CV2025

Compression for Better: A General and Stable Lossless Compression Framework

Boyang Zhang, Daning Cheng, Yunquan Zhang +2

This work focus on how to stabilize and lossless model compression, aiming to reduce model complexity and enhance efficiency without sacrificing performance due to compression erro…

cs.CL2025

PCMind-2.1-Kaiyuan-2B Technical Report

Kairong Luo, Zhenbo Sun, Xinyu Shi +9

The rapid advancement of Large Language Models (LLMs) has resulted in a significant knowledge gap between the open-source community and industry, primarily because the latter relie…

cs.LG2025

A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules

Kairong Luo, Haodong Wen, Shengding Hu +5

Training large models is both resource-intensive and time-consuming, making it crucial to understand the quantitative relationship between model performance and hyperparameters. In…

cs.LG2025

Decoupling Knowledge and Reasoning in Transformers: A Modular Architecture with Generalized Cross-Attention

Zhenyu Guo, Wenguang Chen

Transformers have achieved remarkable success across diverse domains, but their monolithic architecture presents challenges in interpretability, adaptability, and scalability. This…