gated-delta-net

Tag

Cards List
#gated-delta-net

@jiqizhixin: New from NVIDIA! You can edit a model’s compressed memory without scrambling what it already knows! Enter Gated DeltaNe…

X AI KOLs Timeline · 2026-05-22 Cached

NVIDIA introduces Gated DeltaNet-2, a method for editing compressed model memory without catastrophic forgetting, using independent gates for erase and write operations. It outperforms existing models like Mamba-2 and Mamba-3 on language modeling and long-context tasks.

0 favorites 0 likes
#gated-delta-net

@BlinkDL_AI: Gated DeltaNet-2 is almost exactly RWKV-7's DPLR recurrence, not acknowledging the elephant in the room

X AI KOLs Following · 2026-05-22 Cached

Ali Hatamizadeh announces Gated DeltaNet-2, a new linear attention model that outperforms KDA and Mamba-3 at 1.3B scale; @BlinkDL_AI notes its recurrence is nearly identical to RWKV-7's DPLR.

0 favorites 0 likes
← Back to home

Submit Feedback