The released Macaron-V1-Venti model uses a frozen 744B base plus four per-turn-routed LoRA specialists and reports high internal benchmark scores, but it does not demonstrate cross-generation continual-learning gains.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
The released Macaron-V1-Venti model uses a frozen 744B base plus four per-turn-routed LoRA specialists and reports high internal benchmark scores, but it does not demonstrate cross-generation continual-learning gains.