3 papers
cs.LG2026
Why Are Linear RNNs More Parallelizable?
William Merrill, Hongjian Jiang, Yanhong Li +2
The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability. While prior work establishes the expressi…
cs.LG2026
How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
Ming Li, Yanhong Li, Ziyue Li +1
As the post-training of large language models (LLMs) advances from instruction-following to complex reasoning tasks, understanding how different data affect finetuning dynamics rem…
cs.CL2025
What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
Ming Li, Yanhong Li, Tianyi Zhou
What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs) through the lens of the gradient. We…