3 accepted papers
Multimodal Large Language Models (MLLMs) employing the Mixture-of-Experts (MoE) structure exhibit encouraging results in visual language tasks. However, they struggle with catastrophic forgetting due to a lack of effective collaboration among experts and negative transfer across tasks. This happens
Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event, as the relevant supervision is unavailable.…
Multi-style outline controllable generation is crucial for multiple applications, including document semantic structuring and retrieval-augmented generation.The great success of preference alignment approaches encourages their application in controllable generation tasks.However, these attempts enco…