SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs Paper • 2406.19593 • Published Jun 28, 2024
Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning Paper • 2412.03467 • Published Dec 4, 2024 • 1
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging Paper • 2412.19512 • Published Dec 27, 2024 • 9