11 papers
Denser Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Meng Wang, Haohan Zhao, Wenzhuo Liu +7
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgett…
CL-VISTA: Benchmarking Continual Learning in Video Large Language Models
Haiyang Guo, Yichen Shi, Fei Zhu +6
Video Large Language Models (Video-LLMs) require continual learning to adapt to non-stationary real-world data. However, existing benchmarks fall short of evaluating modern foundat…
MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark
Haiyang Guo, Fei Zhu, Hongbo Zhao +5
Continual learning enables AI systems to acquire new knowledge while retaining previously learned information. While traditional unimodal methods have made progress, the rise of Mu…
RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
Fanhu Zeng, Haiyang Guo, Fei Zhu +2
Fine-tuning pre-trained models with custom data leads to numerous expert models on specific tasks. Merging models into one universal model to empower multi-task ability refraining…
ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt
Fanhu Zeng, Fei Zhu, Haiyang Guo +2
Large Multimodal Models (LMMs) exhibit remarkable multi-tasking ability by learning mixed instruction datasets. However, novel tasks would be encountered sequentially in dynamic wo…
Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
Haiyang Guo, Fanhu Zeng, Fei Zhu +9
The rapid advancement of generative models has empowered modern AI systems to comprehend and produce highly sophisticated content, even achieving human-level performance in specifi…