5 papers
Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
Yuhang Han, Xuyang Liu, Zihan Zhang +6
The quadratic complexity of Multimodal Large Language Models (MLLMs) with respect to context length poses significant computational and memory challenges, hindering their real-worl…
VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL
Fengyuan Dai, Zifeng Zhuang, Yufei Huang +4
Diffusion models have emerged as powerful generative tools across various domains, yet tailoring pre-trained models to exhibit specific desirable properties remains challenging. Wh…
Exploring the Evolution of Physics Cognition in Video Generation: A Survey
Minghui Lin, Xiang Wang, Yishan Wang +8
Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical…
M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension
Xuyang Liu, Ting Liu, Siteng Huang +6
Referring expression comprehension (REC) is a vision-language task to locate a target object in an image based on a language expression. Fully fine-tuning general-purpose pre-train…
Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration
Pengxiang Ding, Jianfei Ma, Xinyang Tong +13
This paper addresses the limitations of current humanoid robot control frameworks, which primarily rely on reactive mechanisms and lack autonomous interaction capabilities due to d…