3 papers
cs.CV2026
Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
Yi Yang, Xueqi Li, Yiyang Chen +7
Recent advances in Vision-Language-Action (VLA) models demonstrate that visual signals can effectively complement sparse action supervisions. However, letting VLA directly predict…
cs.LG2025
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
Bokai Lin, Zihao Zeng, Zipeng Xiao +5
KV cache has become a de facto technique for the inference of large language models (LLMs), where tensors of shape (layer number, head number, sequence length, feature dimension) a…
cs.LG2024
Improved Operator Learning by Orthogonal Attention
Zipeng Xiao, Zhongkai Hao, Bokai Lin +2
Neural operators, as an efficient surrogate model for learning the solutions of PDEs, have received extensive attention in the field of scientific machine learning. Among them, att…