Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models? Paper • 2502.11895 • Published Feb 17 • 2
An Extra RMSNorm is All You Need for Fine Tuning to 1.58 Bits Paper • 2505.08823 • Published May 12 • 2
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits Paper • 2402.17764 • Published Feb 27, 2024 • 622
OmniGen2: Exploration to Advanced Multimodal Generation Paper • 2506.18871 • Published 29 days ago • 73 • 4
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 106