InCoder-32B-Thinking: Industrial Code World Model for Thinking Paper • 2604.03144 • Published 9 days ago • 224
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU Paper • 2604.05091 • Published 6 days ago • 39
EXAONE 4.5 Collection LG's First Open-Weight Vision-Language Model for Industrial Intelligence • 3 items • Updated 3 days ago • 28
DFlash Collection Block Diffusion for Flash Speculative Decoding • 13 items • Updated 6 days ago • 48
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? Paper • 2603.24472 • Published 17 days ago • 53
MolmoWeb Collection This is the collection of MolmoWeb artifacts, including model checkpoints and data. • 6 items • Updated 1 day ago • 24