🏢 Northwestern Polytechnical University
Rethinking Token Reduction in MLLMs: Towards a Unified Paradigm for Training-Free Acceleration
·3716 words·18 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Multimodal Learning
Vision-Language Models
🏢 Northwestern Polytechnical University
FiCoCo: A unified paradigm accelerates Multimodal Large Language Model (MLLM) inference by up to 82.4% with minimal performance loss, surpassing state-of-the-art training-free methods.
Material Anything: Generating Materials for Any 3D Object via Diffusion
·4056 words·20 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
3D Vision
🏢 Northwestern Polytechnical University
Material Anything: Generate realistic materials for ANY 3D object via diffusion!