4 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…
EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines
Shuo Zhang, Chaofa Yuan, Ryan Guo +11
While LLM-based agents have shown promise for deep research, most existing approaches rely on fixed workflows that struggle to adapt to real-world, open-ended queries. Recent work…
-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences
Yining Wang, Jinman Zhao, Chuangxin Zhao +3
Reinforcement Learning with Human Feedback (RLHF) has been the dominant approach for improving the reasoning capabilities of Large Language Models (LLMs). Recently, Reinforcement L…
UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models
Xueyan Zhang, Jinman Zhao, Zhifei Yang +4
This paper introduces Uniform Orthogonal Reinitialization Adaptation (UORA), a novel parameter-efficient fine-tuning (PEFT) approach for Large Language Models (LLMs). UORA achieves…