← Search

Jiacheng Jiang

2 accepted papers

2025

Generative Pre-trained Autoregressive Diffusion Transformer

NeurIPS 2025poster

In this work, we present GPDiT, a Generative Pre-trained Autoregressive Diffusion Transformer that unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis, within a continuous latent space. Instead of predicting discrete tokens, GPDiT autoregressively predicts f…

Cited by 0SourceScholar
2024

Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning

CVPR 2024poster

Quantization is of significance for compressing the over-parameterized deep neural models and deploying them on resource-limited devices. Fixed-precision quantization suffers from performance drop due to the limited numerical representation ability. Conversely mixed-precision quantization (MPQ) is a…