ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search Paper • 2609.13356 • Published 21 days ago • 265
khtsly/Luau-Coder-1.0-1.4B-Base-Stage1 Text Generation • 1B • Updated about 18 hours ago • 436 • 1
DepthBench: Measuring How Residual Connections Enable More Computational Depth Paper • 2609.32534 • Published 6 days ago • 31
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models Paper • 2609.34972 • Published 4 days ago • 29
FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation Paper • 2609.27657 • Published 9 days ago • 9
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Paper • 2609.29845 • Published 8 days ago • 100