Kimi Linear: An Expressive, Efficient Attention Architecture
Paper • 2510.26692 • Published • 133
LLM Architectures
-
-
GLM-5: from Vibe Coding to Agentic Engineering
Paper • 2602.15763 • Published • 201 -
Believe Your Model: Distribution-Guided Confidence Calibration
Paper • 2603.03872 • Published • 40 -
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 203 -
Post-Trained MoE Can Skip Half Experts via Self-Distillation
Paper • 2605.18643 • Published • 30 -
MobileMoE: Scaling On-Device Mixture of Experts
Paper • 2605.27358 • Published • 15 -
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Paper • 2606.02437 • Published • 239 -
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Paper • 2606.18023 • Published • 210 -
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Paper • 2607.02980 • Published • 78