view article Article SmolLM - blazingly fast and remarkably powerful By loubnabnl and 2 others • Jul 16, 2024 • 411
OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens Paper • 2504.07096 • Published Apr 9 • 76
FFN Fusion: Rethinking Sequential Computation in Large Language Models Paper • 2503.18908 • Published Mar 24 • 20
Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation Paper • 2503.16430 • Published Mar 20 • 34
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement Paper • 2503.17352 • Published Mar 21 • 24