1 citations · 1 across the 5 of their papers we have counts for
6 papers
DGA-Muon: Decoupled Geometry-Aligned Adaptive Scaling for Muon
Wenpeng Zhang, Runsheng Yu
While NorMuon has achieved strong empirical performance in pretraining, its underlying adaptive mechanism remains largely heuristic and poorly understood. In this work, we provide…
Matrix AdaGrad: Row-wise and Column-wise Adaptive Subgradient Methods
Wenpeng Zhang, Runsheng Yu, Peilin Zhao
Adaptive optimization methods such as AdaGrad and Adam are widely used in modern deep neural network training, but their adaptive scaling is primarily designed for vector-valued pa…
FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
Runzhe Zhang, Letian Chen, Wenpeng Zhang +2
We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the curved sampling trajectories…
Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning
Tianchi Cai, Jiyan Jiang, Wenpeng Zhang +7
We study the budget allocation problem in online marketing campaigns that utilize previously collected offline data. We first discuss the long-term effect of optimizing marketing b…
Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems
Tianchi Cai, Shenliao Bao, Jiyan Jiang +5
Model-free RL-based recommender systems have recently received increasing research attention due to their capability to handle partial feedback and long-term rewards. However, most…
A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning
Tianchi Cai, Wenpeng Zhang, Lihong Gu +2
Although well-established in general reinforcement learning (RL), value-based methods are rarely explored in constrained RL (CRL) for their incapability of finding policies that ca…