Data Party THU
Nov 19, 2026 · Artificial Intelligence
CRAM: Multimodal Models Forget? EMNLP 2026 Reveals Format Conflicts Mimic Forgetting
Nanjing University's CRAM method for multimodal continual instruction tuning isolates conflicting answer formats, reuses shared capabilities, and adaptively allocates LoRA experts via centroid routing and orthogonal constraints, revealing that many apparent forgetting errors are actually format mismatches rather than knowledge loss.
CRAMCatastrophic ForgettingEMNLP 2026
0 likes · 11 min read
