1 citations · 2 across the 5 of their papers we have counts for
4 papers · 1 filter
Principal-timestep Restricted Init via Sparse Matrix-decomposition in Flow-matching
Jiayang Gu, Zheng Fang, Lichaun Xiang +3
Flow-matching diffusion models have recently emerged as a strong paradigm for high-fidelity visual generation. However, their prohibitively high fine-tuning cost limits scalability…
FlexControl: Computation-Aware ControlNet with Differentiable Router for Text-to-Image Generation
Zheng Fang, Lichuan Xiang, Xu Cai +2
ControlNet offers a powerful way to guide diffusion-based generative models, yet most implementations rely on ad-hoc heuristics to choose which network blocks to control-an approac…
No More Adam: Learning Rate Scaling at Initialization is All You Need
Minghao Xu, Lichuan Xiang, Xu Cai +1
In this work, we question the necessity of adaptive gradient methods for training deep neural networks. SGD-SaI is a simple yet effective enhancement to stochastic gradient descent…
Zero-Cost Operation Scoring in Differentiable Architecture Search
Lichuan Xiang, Łukasz Dudziak, Mohamed S. Abdelfattah +3
We formalize and analyze a fundamental component of differentiable neural architecture search (NAS): local "operation scoring" at each operation choice. We view existing operation…