5 papers
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…
A Similarity Network for Correlating Musical Structure to Military Strategy
Yiwen Zhang, Hui Zhang, Fanqin Meng
Music perception, a multi-sensory process based on the synesthesia effect, is an essential component of music aesthetic education. Understanding music structure helps both percepti…
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…
Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness
Lingnan Xu, Chong Feng, Kaiyuan Zhang +3
While large language models (LLMs) demonstrate impressive capabilities, their reliance on parametric knowledge often leads to factual inaccuracies. Retrieval-Augmented Generation (…
Enhancing Speech Emotion Recognition with Multi-Task Learning and Dynamic Feature Fusion
Honghong Wang, Jing Deng, Fanqin Meng +1
This study investigates fine-tuning self-supervised learn ing (SSL) models using multi-task learning (MTL) to enhance speech emotion recognition (SER). The framework simultane ousl…