Zhao Song

Learning Sigmoid Belief Networks via Monte Carlo Expectation Maximization

2016 · International Conference on Artificial Intelligence and Statistics

Belief networks are commonly used generative models of data, but require expensive posterior estimation to train and test the model. Learning typically proceeds by posterior sampling, variational approximations, or recognition networks, combined with stochastic optimization. …

Reducing approximate Longest Common Subsequence to approximate Edit Distance

2019 · Society for Industrial and Applied Mathematics eBooks

Given a pair of n-character strings, the problems of computing their Longest Common Subsequence and Edit Distance have been extensively studied for decades. For exact algorithms, LCS and Edit Distance (with character insertions and deletions) …

A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer

2023 · arXiv (Cornell University)

The Deep Leakage from Gradient (DLG) attack has emerged as a prevalent and highly effective method for extracting sensitive training data by inspecting exchanged gradients. This approach poses a substantial threat to the privacy of …

Thinking Isn’t an Illusion

2025 · SuperIntelligence - Robotics - Safety & Alignment

Large Reasoning Models (LRMs) have become a central focus in today’s large language model (LLM) research, where models are designed to output a step-by-step thinking process before arriving at a final answer to handle complex …