Kaifeng Lyu
- Papers
- 9
Cite
Notes
Only stored in your browser.
9papers
Authored papers
9A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
arXiv 2025
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?
arXiv 2025
AI-Assisted Generation of Difficult Math Questions
arXiv 2024
Safety Alignment Should Be Made More Than Just a Few Tokens Deep
arXiv 2024
RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval
arXiv 2024
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
arXiv 2024
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
arXiv 2023
A Quadratic Synchronization Rule for Distributed Deep Learning
arXiv 2023
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
arXiv 2022
Affiliations
No known affiliations.
Frequent co-authors
10from 9 papers