Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs Paper • 2510.18279 • Published 8 days ago • 3
How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients Paper • 2504.10766 • Published Apr 14 • 40
Grounded Persuasive Language Generation for Automated Marketing Paper • 2502.16810 • Published Feb 24 • 12
What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective Paper • 2410.23743 • Published Oct 31, 2024 • 63