Jamba-1.5 Collection The AI21 Jamba family of models are state-of-the-art, hybrid SSM-Transformer instruction following foundation models • 2 items • Updated Aug 22 • 82
LMDX: Language Model-based Document Information Extraction and Localization Paper • 2309.10952 • Published Sep 19, 2023 • 65
RealCompo: Dynamic Equilibrium between Realism and Compositionality Improves Text-to-Image Diffusion Models Paper • 2402.12908 • Published Feb 20 • 9
Data Engineering for Scaling Language Models to 128K Context Paper • 2402.10171 • Published Feb 15 • 23
Premise Order Matters in Reasoning with Large Language Models Paper • 2402.08939 • Published Feb 14 • 27
Computing Power and the Governance of Artificial Intelligence Paper • 2402.08797 • Published Feb 13 • 12
Transformers Can Achieve Length Generalization But Not Robustly Paper • 2402.09371 • Published Feb 14 • 13
GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency Paper • 2402.08855 • Published Feb 13 • 11
Unifying Vision, Text, and Layout for Universal Document Processing Paper • 2212.02623 • Published Dec 5, 2022 • 10
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper • 2402.13753 • Published Feb 21 • 112
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement Paper • 2402.14658 • Published Feb 22 • 82
Improving Text Embeddings with Large Language Models Paper • 2401.00368 • Published Dec 31, 2023 • 79
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry Paper • 2402.04347 • Published Feb 6 • 13