coarse-to-fine attention 1diffusion transformers 1multimodal fusion 1rectified flow matching 1text-guided audio editing 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.SD2026
RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers
Liting Gao, Yonggang Zhu, Yaru Chen +5
The paper introduces RFM-Editing 2, a text‑guided audio editing system that uses rectified flow matching and a two‑stage diffusion transformer with a coarse‑to‑fine attention schem…
cs.NI2025
Task-Oriented Multimodal Token Transmission in Resource-Constrained Multiuser Networks
Junhe Zhang, Wanli Ni, Pengwei Wang +1
With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may resu…
cs.LG2024
Federated Split Learning with Model Pruning and Gradient Quantization in Wireless Networks
Junhe Zhang, Wanli Ni, Dongyu Wang
As a paradigm of distributed machine learning, federated learning typically requires all edge devices to train a complete model locally. However, with the increasing scale of artif…