3 papers
cs.LG2026
Accelerating Visual On-Policy Distillation with Batched Speculative Jacobi Rollouts
Bingqi Shan, Zhehao Yu, Kenhong Lin +1
Visual on-policy distillation (OPD) improves the training of compact visual autoregressive models by learning from trajectories generated by the current student. However, these onl…
cs.CV2026
S2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain
Baoquan Zhang, Zhehao Yu, Lisai Zhang +5
Parameter Efficient Fine-Tuning (PEFT) is a key technique for adapting a large pretrained model to downstream tasks by fine-tuning only a small number of parameters. Recent methods…
cs.CV2026
SJD-PV: Speculative Jacobi Decoding with Phrase Verification for Autoregressive Image Generation
Zhehao Yu, Baoquan Zhang, Bingqi Shan +5
Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing trainin…