moonshotai/Kimi-Linear-48B-A3B-Instruct Text Generation • 49B • Updated Dec 16, 2025 • 31.8k • 541
MIND: Benchmarking Memory Consistency and Action Control in World Models Paper • 2602.08025 • Published 5 days ago • 9
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published 8 days ago • 301
Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers Paper • 2512.17351 • Published Dec 19, 2025 • 28
Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments Paper • 2601.01075 • Published Jan 3 • 6
Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments Paper • 2601.01075 • Published Jan 3 • 6
Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments Paper • 2601.01075 • Published Jan 3 • 6