activity
20162026
most citedEarly Dark Energy Can Resolve The Hubble Tension

1k citations · 3.7k across the 27 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…