6 papers
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +339
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that…
SystolicAttention: Fusing FlashAttention within a Single Systolic Array
Jiawei Lin, Yuanlong Li, Guokai Chen +1
Transformer models rely heavily on the scaled dot-product attention (SDPA) operation, typically implemented as FlashAttention. Characterized by its frequent interleaving of matrix…
A Training-Free Approach for Multi-ID Customization via Attention Adjustment and Spatial Control
Jiawei Lin, Guanlong Jiao, Jianjin Xu
Multi-ID customization is an interesting topic in computer vision and attracts considerable attention recently. Given the ID images of multiple individuals, its purpose is to gener…
High-Altitude Balloon Station-Keeping with First Order Model Predictive Control
Myles Pasetsky, Jiawei Lin, Bradley Guo +1
High-altitude balloons (HABs) are common in scientific research due to their wide range of applications and low cost. Because of their nonlinear, underactuated dynamics and the par…
PrioriTouch: Adapting to User Contact Preferences for Whole-Arm Physical Human-Robot Interaction
Rishabh Madan, Jiawei Lin, Mahika Goel +10
Physical human-robot interaction (pHRI) requires robots to adapt to individual contact preferences, such as where and how much force is applied. Identifying preferences is difficul…