Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
FlowTrain: Flow-Based Decoupled Training for Industrial-Grade Vision-Language Models
Zhida Jiang, Zhaolong Xing, Yang Pei +14
Industrial-grade distributed training of vision-language models (VLMs) remains far less efficient than that of unimodal LLMs. Existing solutions either follow a monolithic design t…
cs.LG2026
Distribution-Free Pretraining of Classification Losses via Evolutionary Dynamics
Meng Xiang, Yan Pei
We propose Evolutionary Dynamic Loss (EDL), a framework that learns a transferable classification loss in the probability space using unlimited synthetic prediction-label pairs, wi…
cs.LG2025
Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions
Yan Ru Pei
We introduce Centaurus, a class of networks composed of generalized state-space model (SSM) blocks, where the SSM operations can be treated as tensor contractions during training.…