Yongzhong Xu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1
Research Timeline
2026
When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures
The paper tracks the developmental emergence of attention circuits in 1B-class language models, finding that the formation of induction and attention-sink circuits are distinct, temporally separated transitions.
Highlighted terms show continued research focus across papers