4 papers · 1 filter
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Xudong Tan, Yaoxin Yang, Peng Ye +5
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot control through natural language instructions. However, their high inference cost-…
GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts
Minwen Liao, Hao Bo Dong, Xinyi Wang +3
Low-light enhancement has wide applications in autonomous driving, 3D reconstruction, remote sensing, surveillance, and so on, which can significantly improve information utilizati…
KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities
Hsin-Ping Huang, Xinyi Wang, Yonatan Bitton +8
Recent advances in text-to-image generation have improved the quality of synthesized images, but evaluations mainly focus on aesthetics or alignment with text prompts. Thus, it rem…
Seeing through the Mask: Multi-task Generative Mask Decoupling Face Recognition
Zhaohui Wang, Sufang Zhang, Jianteng Peng +2
The outbreak of COVID-19 pandemic make people wear masks more frequently than ever. Current general face recognition system suffers from serious performance degradation,when encoun…