Vision-language pre-trained models have achieved impressive performance on various
downstream tasks. However their large model sizes hinder their utilization on platforms with …

Large-scale video-language pre-training has made remarkable strides in advancing video-
language understanding tasks. However, the heavy computational burden of video …

Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the
impressive performance. However, their expensive computation costs, ie, throughput and …

Abstract Vision-Language Transformers (VLTs) have shown great success recently but are
meanwhile accompanied by heavy computation costs where a major reason can be …

Token compression expedites the training and inference of Vision Transformers (ViTs) by
reducing the number of the redundant tokens, eg, pruning inattentive tokens or merging …

Multimodal large language models (MLLMs) enhance their perceptual capabilities by
integrating visual and textual information. However, processing the massive number of …

With the advancement of large-scale language modeling techniques, large multimodal
models combining visual encoders with large language models have demonstrated …

Recently, multimodal large language models (MM-LLMs) have achieved great success in
many multimodal tasks, but their high computational costs limit their further promotion and …

We study the capability of Video-Language (VidL) models in understanding compositions
between objects, attributes, actions and their relations. Composition understanding …

Efficient inference in Large Language Models (LLMs) is impeded by the growing memory
demands of key-value (KV) caching, especially for longer sequences. Traditional KV cache …