5 papers
UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
Hao Wu, Xudong Wang, Jialiang Zhang +5
One-stream Transformer-based trackers achieve advanced performance in visual object tracking but suffer from significant computational overhead that hinders real-time deployment. W…
Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models
Junyan Lin, Junlong Tong, Hao Wu +4
Multimodal Large Language Models (MLLMs) have achieved strong performance across many tasks, yet most systems remain limited to offline inference, requiring complete inputs before…
Multimodal Language Models See Better When They Look Shallower
Haoran Chen, Junyan Lin, Xinghao Chen +6
Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however,…
Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices
Junyan Lin, Haoran Chen, Yue Fan +5
Multimodal Large Language Models (MLLMs) have made significant advancements in recent years, with visual features playing an increasingly critical role in enhancing model performan…
To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimodal Large Language Models
Junyan Lin, Haoran Chen, Dawei Zhu +1
In recent years, multimodal large language models (MLLMs) have garnered significant attention from both industry and academia. However, there is still considerable debate on constr…