CGM derives optimal soft and hard mixing strategies for MLLM parameters via curvature-aware second-order analysis to improve the specialization versus forgetting trade-off.
arXiv preprint arXiv:2503.04543 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
I2P adaptively selects the most discriminative layers from visual foundation models for synthetic image detection and constrains task updates to low-sensitivity parameter subspaces to improve specificity without harming generalization.
citing papers explorer
-
Curvature-Guided Mixing for MLLM Adaptation
CGM derives optimal soft and hard mixing strategies for MLLM parameters via curvature-aware second-order analysis to improve the specialization versus forgetting trade-off.
-
Adaptive Forensic Feature Refinement via Intrinsic Importance Perception
I2P adaptively selects the most discriminative layers from visual foundation models for synthetic image detection and constrains task updates to low-sensitivity parameter subspaces to improve specificity without harming generalization.