activity
20242026
most citedPERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching

3 citations · 5 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

DGNet: Discrete Green Networks for Data-Efficient Learning of Spatiotemporal PDEs

Yingjie Tan, Quanming Yao, Yaqing Wang

Spatiotemporal partial differential equations (PDEs) underpin a wide range of scientific and engineering applications. Neural PDE solvers offer a promising alternative to classical…

cs.LG2026

Self-Generative Adversarial Fine-Tuning for Large Language Models

Shiguang Wu, Yaqing Wang, Quanming Yao

Fine-tuning large language models (LLMs) for alignment typically relies on supervised fine-tuning or reinforcement learning from human feedback, both limited by the cost and scarci…

cs.LG2025

Spectral Alignment as Predictor of Loss Explosion in Neural Network Training

Haiquan Qiu, You Wu, Yingjie Tan +2

Loss explosions in training deep neural networks can nullify multi-million dollar training runs. Conventional monitoring metrics like weight and gradient norms are often lagging an…

cs.LG2025

Attending on Multilevel Structure of Proteins enables Accurate Prediction of Cold-Start Drug-Target Interactions

Ziying Zhang, Yaqing Wang, Yuxuan Sun +2

Cold-start drug-target interaction (DTI) prediction focuses on interaction between novel drugs and proteins. Previous methods typically learn transferable interaction patterns betw…

cs.LG2024

Learning to Learn with Contrastive Meta-Objective

Shiguang Wu, Yaqing Wang, Yatao Bian +1

Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans. Different meta-learning approaches all work under/with the mini-batch episodic training fra…

cs.LG2024

Beyond Scaleup: Knowledge-aware Parsimony Learning from Deep Networks

Quanming Yao, Yongqi Zhang, Yaqing Wang +3

The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due t…