arxiv:2509.25049
Bingrui Li
Bingrui
AI & ML interests
None yet
Recent Activity
authored
a paper
2 days ago
On the Optimization and Generalization of Two-layer Transformers with
Sign Gradient Descent
upvoted
a
paper
13 days ago
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative
Decoders
authored
a paper
about 1 month ago
Memory Efficient Optimizers with 4-bit States
Organizations
None yet
