8 papers
HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models
Yansong Guo, Chaoyang Zhu, Jiayi Ji +2
Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computat…
SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia
Pengfei Yue, Xingran Zhao, Juntao Chen +6
Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on…
3D-DRES: Detailed 3D Referring Expression Segmentation
Qi Chen, Changli Wu, Jiayi Ji +2
Current 3D visual grounding tasks only process sentence level detection or segmentation, which critically fails to leverage the rich compositional contextual reasonings within natu…
Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation
Yilong Yang, Jianxin Tian, Shengchuan Zhang +1
Current zero-shot Camouflaged Object Segmentation methods typically employ a two-stage pipeline (discover-then-segment): using MLLMs to obtain visual prompts, followed by SAM segme…
Test-Time Computing for Referring Multimodal Large Language Models
Mingrui Wu, Hao Chen, Jiayi Ji +5
We propose ControlMLLM++, a novel test-time adaptation framework that injects learnable visual prompts into frozen multimodal large language models (MLLMs) to enable fine-grained r…
MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation
Changli Wu, Haodong Wang, Jiayi Ji +5
Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with o…