Siteng Huang

huangsiteng's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a paper 6 days ago

Rethinking Token Reduction in MLLMs: Towards a Unified Paradigm for Training-Free Acceleration

Paper • 2411.17686 • Published 6 days ago • 18

upvoted a paper 3 months ago

PiTe: Pixel-Temporal Alignment for Large Video-Language Model

Paper • 2409.07239 • Published Sep 11 • 11

upvoted a paper 9 months ago

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

Paper • 2403.14520 • Published Mar 21 • 33