collaborators

9 papers

cs.LG2026

Muon in Associative Memory Learning: Training Dynamics and Scaling Laws

Binghui Li, Kaifei Wang, Han Zhong +2

Muon updates matrix parameters via the matrix sign of the gradient and has shown strong empirical gains, yet its dynamics and scaling behavior remain unclear in theory. We study Mu…

cs.CL2026

Understanding the Ability of LLMs to Handle Character-Level Perturbation

Anyuan Zhuo, Xuefei Ning, Ningyuan Li +3

This work investigates the resilience of contemporary large language models (LLMs) against frequent character-level perturbations. We examine three types of character-level perturb…

cs.LG2026

Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise

Linyu Liu, Pinyan Lu

Highly over-parameterized models can simultaneously memorize noisy labels and generalize well, yet how these behaviors coexist remains poorly understood. In this work, we investiga…

cs.LG2026

SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning

Zhengyang Ai, Zikang Shan, Xiaodong Ai +3

Process supervision has emerged as a promising approach for enhancing LLM reasoning, yet existing methods fail to distinguish meaningful progress from mere verbosity, leading to li…

cs.AI2026

Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use

Hanbing Liu, Chunhao Tian, Nan An +4

We study budget-constrained tool-augmented agents, where a large language model must solve multi-step tasks by invoking external tools under a strict monetary budget. We formalize…

cs.LG2026

BAPS: A Fine-Grained Low-Precision Scheme for Softmax in Attention via Block-Aware Precision reScaling

Zisheng Ye, Xiaoyu He, Maoyuan Song +10

As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck…