Models that adapt to a stream of tasks without forgetting prior capabilities still struggle to isolate updates between different LoRA experts. PASs-MoE creates separate pathway activation subspaces for each expert, which helps mitigate misaligned co-drift. If your MLLM pipeline relies on continual instruction tuning, this could be a game-changer.
STATUS
ACTIVE
CATEGORY
Models
SOURCES
1 linked
ENTITIES
3 detected
OVERRIDE
Automated
MOMENTUM
3 days ago