🏢 Tsinghua Shenzhen International Graduate School
Unleashing Region Understanding in Intermediate Layers for MLLM-based Referring Expression Generation
·2269 words·11 mins·
loading
·
loading
Natural Language Processing
Large Language Models
🏢 Tsinghua Shenzhen International Graduate School
Unlocking intermediate layers in MLLMs improves referring expression generation by enhancing accuracy and detail while reducing hallucinations.
MambaTree: Tree Topology is All You Need in State Space Model
·1962 words·10 mins·
loading
·
loading
Image Classification
🏢 Tsinghua Shenzhen International Graduate School
MambaTree: A novel tree-topology-based state space model surpasses existing methods by dynamically generating input-aware topologies for enhanced long-range dependencies in vision and language.