๐ฌ Long video generation is bottlenecked by KV-cache memory. We fixed it.
Presenting QuantVideoGen @ #
ICML2026#:
โก ~7ร smaller KV cache @ INT2
๐พ ~85% less memory
๐ง No fine-tuning, no weight changes
๐ Poster: Thu Jul 9, 2026. 5:00 PM -6:45 PM KST ยท Hall A #
4603#
My wonderful co-author Xingyang Li will be presenting our papers. Come say hi!
๐