50 citations · 86 across the 10 of their papers we have counts for
11 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 +333
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…
Evolving Without Ending: Unifying Multimodal Incremental Learning for Continual Panoptic Perception
Bo Yuan, Danpei Zhao, Wentao Li +2
Continual learning (CL) is a great endeavour in developing intelligent perception AI systems. However, the pioneer research has predominantly focus on single-task CL, which restric…
Dual-Stream Spectral Decoupling Distillation for Remote Sensing Object Detection
Xiangyi Gao, Danpei Zhao, Bo Yuan +1
Knowledge distillation is an effective and hardware-friendly method, which plays a key role in lightweighting remote sensing object detection. However, existing distillation method…
Rank-Aware Agglomeration of Foundation Models for Immunohistochemistry Image Cell Counting
Zuqi Huang, Mengxin Tian, Huan Liu +6
Accurate cell counting in immunohistochemistry (IHC) images is critical for quantifying protein expression and aiding cancer diagnosis. However, the task remains challenging due to…
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…
Kimi K2: Open Agentic Intelligence
Kimi Team, Yifan Bai, Yiping Bao +195
We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which…
Reconciling Semantic Controllability and Diversity for Remote Sensing Image Synthesis with Hybrid Semantic Embedding
Junde Liu, Danpei Zhao, Bo Yuan +2
Significant advancements have been made in semantic image synthesis in remote sensing. However, existing methods still face formidable challenges in balancing semantic controllabil…
Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images
Bo Yuan, Danpei Zhao, Zhuoran Liu +2
Continual learning (CL) breaks off the one-way training manner and enables a model to adapt to new data, semantics and tasks continuously. However, current CL methods mainly focus…
Panoptic Perception: A Novel Task and Fine-grained Dataset for Universal Remote Sensing Image Interpretation
Danpei Zhao, Bo Yuan, Ziqiang Chen +4
Current remote-sensing interpretation models often focus on a single task such as detection, segmentation, or caption. However, the task-specific designed models are unattainable t…
PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection
Wentao Li, Danpei Zhao, Bo Yuan +2
Fine-grained object detection (FGOD) extends object detection with the capability of fine-grained recognition. In recent two-stage FGOD methods, the region proposal serves as a cru…