activity
20202026
most citedA dark matter profile to model diverse feedback-induced core sizes of CDM haloes

160 citations · 275 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

Xiaofeng Mao, Shaohao Rui, Kaining Ying +4

Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compoundin…