3 citations · 8 across the 10 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Compression Forcing: Hierarchical History Tokenization Enables Flexible World Models
Siqiao Huang, Partha Kaushik, Michael Chen +5
Effective world modeling requires compressing salient history information that facilitates future prediction. However, most existing approaches inherit tokenization and conditionin…
cs.CV2026
Nano World Models: A Minimalist Implementation of Future Video Prediction
Siqiao Huang, Partha Kaushik, Michael Chen +5
World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale…