3 papers
cs.LG2026
Variance-Adaptive Muon: Pre-Orthogonalization Variance Modulation for Efficient Language Model Pretraining
Jingru Li, Yibo Fan, Huan Li
Optimizer design plays a central role in efficient language model pretraining, directly affecting optimization dynamics, convergence speed, and compute cost under fixed training bu…
cs.CV2025
RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy
Aiyue Chen, Bin Dong, Jingru Li +4
Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computati…
cs.LG2025
AFD-STA: Adaptive Filtering Denoising with Spatiotemporal Attention for Chaotic System Prediction
Chunlin Gong, Yin Wang, Jingru Li +1
This paper presents AFD-STA Net, a neural framework integrating adaptive filtering and spatiotemporal dynamics learning for predicting high-dimensional chaotic systems governed by…