13 papers
ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs
Yuhao Wang, Mu Qiao, Haiwen Diao +5
Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token sequences. Training-free visual token reduction provides an efficient solution.…
VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?
Qing'an Liu, Juntong Feng, Yuhao Wang +6
Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pur…
Regularizing Subspace Redundancy of Low-Rank Adaptation
Yue Zhu, Haiwen Diao, Shang Gao +8
Low-Rank Adaptation (LoRA) and its variants have delivered strong capability in Parameter-Efficient Transfer Learning (PETL) by minimizing trainable parameters and benefiting from…
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
Haiwen Diao, Xiaotong Li, Yufeng Cui +6
Existing encoder-free vision-language models (VLMs) are rapidly narrowing the performance gap with their encoder-based counterparts, highlighting the promising potential for unifie…
End-to-End Vision Tokenizer Tuning
Wenxuan Wang, Fan Zhang, Yufeng Cui +5
Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks…
Exploring Dynamic Transformer for Efficient Object Tracking
Jiawen Zhu, Xin Chen, Haiwen Diao +6
The speed-precision trade-off is a critical problem for visual object tracking which usually requires low latency and deployment on constrained resources. Existing solutions for ef…