activity
20242026
collaborators

7 papers

cs.LG2026

Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks

Tianyu Pang, Vignesh Kothapalli, Shenyang Deng +3

We study optimal learning-rate selection in two-layer and three-layer linear neural networks trained to learn linear target functions. In particular, we derive the exact closed-for…

cs.LG2025

Data Value in the Age of Scaling: Understanding LLM Scaling Dynamics Under Real-Synthetic Data Mixtures

Haohui Wang, Jingyuan Qi, Jianpeng Chen +9

The rapid progress of large language models (LLMs) is fueled by the growing reliance on datasets that blend real and synthetic data. While synthetic data offers scalability and cos…

cs.LG2025

HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations

Shuaicheng Zhang, Haohui Wang, Junhong Lin +5

Graph heterophily, where connected nodes have different labels, has attracted significant interest recently. Most existing works adopt a simplified approach - using low-pass filter…

cs.LG2025

EVINET: Towards Open-World Graph Learning via Evidential Reasoning Network

Weijie Guan, Haohui Wang, Jian Kang +2

Graph learning has been crucial to many real-world tasks, but they are often studied with a closed-world assumption, with all possible labels of data known a priori. To enable effe…

cs.LG2025

LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection

Xinyue Zeng, Haohui Wang, Junhong Lin +3

The proliferation of open-sourced Large Language Models (LLMs) and diverse downstream tasks necessitates efficient model selection, given the impracticality of fine-tuning all cand…

physics.optics2025

MetamatBench: Integrating Heterogeneous Data, Computational Tools, and Visual Interface for Metamaterial Discovery

Jianpeng Chen, Wangzhi Zhan, Haohui Wang +10

Metamaterials, engineered materials with architected structures across multiple length scales, offer unprecedented and tunable mechanical properties that surpass those of conventio…