Effective Distillation to Hybrid xLSTM Architectures
Paper • 2603.15590 • Published • 32
Niklas Schmidinger
smdrnks
AI & ML interests
None yet
Recent Activity
upvoted a paper 23 days ago
Effective Distillation to Hybrid xLSTM Architectures new activity 7 months ago
recursal/QRWKV6-7B-Base:Model produces gibberish new activity 7 months ago
nvidia/Nemotron-CC-v2:Acess RequestOrganizations
None yet
upvoted a paper 23 days ago