Efficient Agentic Reasoning Through Self-Regulated Simulative Planning Paper • 2605.22138 • Published 5 days ago • 7
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models Paper • 2605.07721 • Published 18 days ago • 29
MIND: Benchmarking Memory Consistency and Action Control in World Models Paper • 2602.08025 • Published Feb 8 • 14
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published Feb 5 • 354
Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers Paper • 2512.17351 • Published Dec 19, 2025 • 28