Progressive Multimodal Alignment for Continual Instruction Tuning
Ranking
Overall
69
Content
80
Popularity
44
Observed public metrics from 1 member.
Merged summary
TL;DR - Progressive Multimodal Alignment (PMA) addresses projector-level forgetting during continual instruction tuning of multimodal LLMs. It selectively adds projector experts while retaining the pretrained projector as a stable alignment anchor.
- Detects multimodal distribution shifts using a lightweight representation descriptor.
- Expands projector experts only when needed, enabling sub-linear parameter growth.
- Routes multimodal features across experts to balance adaptation with retention.
- Improves prior methods across two MCIT benchmarks and multiple MLLM backbones.
Sources (1)
Progressive Multimodal Alignment for Continual Instruction Tuning
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - Progressive Multimodal Alignment (PMA) addresses projector-level forgetting during continual instruction tuning of multimodal LLMs. It selectively adds projector experts while retaining the pretrained projector as a stable alignment anchor.
- Detects multimodal distribution shifts using a lightweight representation descriptor.
- Expands projector experts only when needed, enabling sub-linear parameter growth.
- Routes multimodal features across experts to balance adaptation with retention.
- Improves prior methods across two MCIT benchmarks and multiple MLLM backbones.