4 papers
VideoPerceiver: Enhancing Fine-Grained Temporal Perception in Video Multimodal Large Language Models
Fufangchen Zhao, Liao Zhang, Daiqi Shi +5
We propose VideoPerceiver, a novel video multimodal large language model (VMLLM) that enhances fine-grained perception in video understanding, addressing VMLLMs' limited ability to…
On Convergence of the Secant Method
Yan Tan, Chenhao Ye, Qinghai Zhang +1
The secant method, as an important approach for solving nonlinear equations, is introduced in nearly all numerical analysis textbooks. However, most textbooks only briefly address…
Learning without Global Backpropagation via Synergistic Information Distillation
Chenhao Ye, Ming Tang
Backpropagation (BP), while foundational to deep learning, imposes two critical scalability bottlenecks: update locking, where network modules remain idle until the entire backward…
Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection
Wei Ye, Chaoya Jiang, Haiyang Xu +6
Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models. Although previous VLP research has demonstrated the effica…