← Search

Haoran Fang

2 accepted papers

2026

Trajectory-Aware Spiking DiTs Conversion via Membrane Potential Error-Feedback

ICML 2026poster

Diffusion Transformers (DiTs) have achieved state-of-the-art generative performance, yet their iterative denoising process remains computationally expensive and energy-intensive. Spiking Neural Networks (SNNs) offer a promising neuromorphic alternative for energy efficiency; however, the non-differe…

Cited by 0SourceScholar
2025

Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies

NeurIPS 2025poster

Vertical Federated Learning (VFL) enables participants to collaboratively train models on aligned samples while keeping their heterogeneous features private and distributed. Despite their utility, VFL models remain vulnerable to adversarial attacks during inference. Adversarial Training (AT), which…

Cited by 0SourceScholar