5 papers
Kimi Linear: An Expressive, Efficient Attention Architecture
Kimi Team, Yu Zhang, Zongyu Lin +57
We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios -- including s…
OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
Fanqi Lin, Ruiqian Nai, Yingdong Hu +3
General-purpose robots capable of performing diverse tasks require synergistic reasoning and acting capabilities. However, recent dual-system approaches, which separate high-level…
LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
Juzheng Zhang, Jiacheng You, Ashwinee Panda +1
Low-Rank Adaptation (LoRA) has emerged as a popular parameter-efficient fine-tuning (PEFT) method for Large Language Models (LLMs), yet it still incurs notable overhead and suffers…
Fine-Tuning Hard-to-Simulate Objectives for Quadruped Locomotion: A Case Study on Total Power Saving
Ruiqian Nai, Jiacheng You, Liu Cao +4
Legged locomotion is not just about mobility; it also encompasses crucial objectives such as energy efficiency, safety, and user experience, which are vital for real-world applicat…
SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation
Shengjie Wang, Jiacheng You, Yihang Hu +2
Real-world tasks such as garment manipulation and table rearrangement demand robots to perform generalizable, highly precise, and long-horizon actions. Although imitation learning…