4 citations · 7 across the 7 of their papers we have counts for
8 papers
RINS: Residual-Image Neural Subspace Solvers for Large Sparse Linear Systems
Zhongyan Ouyang, Weixin Liao, Mingquan Feng +2
Large sparse linear systems from PDE discretizations require correction subspaces whose operator images explain the current residual. We study this residual-image viewpoint and pro…
ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning
Xiaohan Qin, Xiaoxing Wang, Ning Liao +5
Data quality plays a critical role in enhancing supervised fine-tuning (SFT) for large language models (LLMs), and token-level data selection has emerged as a promising direction f…
Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data?
Shaobo Wang, Cong Wang, Wenjie Fu +11
As the demand for comprehensive evaluations of diverse model capabilities steadily increases, benchmark suites have correspondingly grown significantly in scale. Despite notable ad…
KITINet: KInetic Theory Inspired Inter-Channel Information Exchange for Residual Networks
Mingquan Feng, Yifan Fu, Tongcheng Zhang +3
Residual connections are foundational to modern neural networks, yet the standard additive update provides no explicit mechanism for structured inter-channel interaction. We introd…
KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches
Mingquan Feng, Yixin Huang, Yifan Fu +2
The design of effective optimization algorithms for neural networks remains a fundamental challenge, and most existing methods rely on heuristic extensions of gradient-based update…
Optimal Control Operator Perspective and a Neural Adaptive Spectral Method
Mingquan Feng, Zhijie Chen, Yixin Huang +2
Optimal control problems (OCPs) involve finding a control function for a dynamical system such that a cost functional is optimized. It is central to physical systems in both academ…
Learning Neural Hamiltonian Dynamics: A Methodological Overview
Zhijie Chen, Mingquan Feng, Junchi Yan +1
The past few years have witnessed an increased interest in learning Hamiltonian dynamics in deep learning frameworks. As an inductive bias based on physical laws, Hamiltonian dynam…
Perception Improvement for Free: Exploring Imperceptible Black-box Adversarial Attacks on Image Classification
Yongwei Wang, Mingquan Feng, Rabab Ward +2
Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size i…