Ex-NVIDIA intern shares world-model memory research built on Matrix-Game 2.0
cindy_x_wu · x · 2026-11-21
Researcher cindyxwu thanks NVIDIA for an internship and shares her Princeton/UofT/Vector Institute work on memory in visual world models, built on Matrix-Game 2.0 and LingBot-World, and points to related lines like MemRoPE, ∞-RoPE, YaRN and MosaicMem.
More from Research
- METR's Time Horizon 2.0 report ships too few appendices, researchers complain — leaked topic list — dfrsrchtwts · 2026-11-21
- Proposed proof of Generalized Riemann Hypothesis released; mathematician stresses it is entirely human, no AI — paulabartabajo_ · 2026-11-21
- Arcfront turns real hospital and factory work records into RL environments and frontier model evals — rohanpaul_ai · 2026-11-21
- Goodfire probes Inkling 2 Mini: looped model layers read from "future" layers — fatihdin4en · 2026-11-21
- Terence Tao offers a bet to anyone who really believes RH will be proved next year — jaivin · 2026-11-21
- Terence Tao: AI is winning at math but we've learned almost nothing from it — bansalg_ · 2026-11-21