6 papers
Whisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM Training
Jielin Qiu, Ming Zhu, Wenting Zhao +11
Audio-native large language models (audio-LLMs) commonly use Whisper as their audio encoder. However, Whisper was trained exclusively on speech data, producing weak representations…
Device-Conditioned Neural Architecture Search for Efficient Robotic Manipulation
Yiming Wu, Huan Wang, Zhenghao Chen +2
The growing complexity of visuomotor policies poses significant challenges for deployment with heterogeneous robotic hardware constraints. However, most existing model-efficient ap…
On-Device Diffusion Transformer Policy for Efficient Robot Manipulation
Yiming Wu, Huan Wang, Zhenghao Chen +2
Diffusion Policies have significantly advanced robotic manipulation tasks via imitation learning, but their application on resource-constrained mobile platforms remains challenging…
MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs
Hui Sun, Shiyin Lu, Huanyu Wang +5
Video large language models (Video-LLMs) have made significant progress in understanding videos. However, processing multiple frames leads to lengthy visual token sequences, presen…
Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models
Yiming Wu, Zhenghao Chen, Huan Wang +1
The high computational cost and slow inference time are major obstacles to deploying Video Diffusion Models (VDMs). To overcome this, we introduce a new Video Diffusion Model Compr…
Frame-Voyager: Learning to Query Frames for Video Large Language Models
Sicheng Yu, Chengkai Jin, Huanyu Wang +9
Video Large Language Models (Video-LLMs) have made remarkable progress in video understanding tasks. However, they are constrained by the maximum length of input tokens, making it…