5 citations · 5 across the 7 of their papers we have counts for
7 papers
Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models
Yahong Wang, Zhangkai Ni, Juncheng Wu +3
Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images. While token pruning has emer…
Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming
Menglin Han, Yang Ding, Yulei Lu +6
Real-time long-form avatar audio-video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consistency. Adapting a pretrained…
LoMeVQA: A Comprehensive Benchmark for Longitudinal Medical VQA
Zhilin Wu, Zhangkai Ni, Chengmei Yang +4
In clinical practice, patients often undergo multiple imaging examinations over successive visits, yielding longitudinal data. Modeling such temporal information is crucial for rel…
FlowBypass: Rectified Flow Trajectory Bypass for Training-Free Image Editing
Menglin Han, Zhangkai Ni
Training-free image editing has attracted increasing attention for its efficiency and independence from training data. However, existing approaches predominantly rely on inversion-…
EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
Yahong Wang, Juncheng Wu, Zhangkai Ni +6
Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective…
Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
Hongbi Zhou, Zhangkai Ni
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis. However, existing methods struggle to adaptively optimize the distribution of Gaussian pr…
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
Kerui Ren, Lihan Jiang, Tao Lu +4
The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and efficiency compared to NeRF-based neural scene representations. While demonstrating the potenti…