activity
20192025
most citedPurifying Adversarial Perturbation with Adversarially Trained Auto-encoders

3 citations · 6 across the 5 of their papers we have counts for

collaborators

5 papers

cs.PL2025

Kernel-FFI: Transparent Foreign Function Interfaces for Interactive Notebooks

Hebi Li, Forrest Sheng Bao, Qi Xiao +1

Foreign Function Interfaces (FFIs) are essential for enabling interoperability between programming languages, yet existing FFI solutions are ill-suited for the dynamic, interactive…

cs.SE2023

CodePod: A Language-Agnostic Hierarchical Scoping System for Interactive Development

Hebi Li, Forrest Sheng Bao, Qi Xiao +1

Interactive development environments like Jupyter Notebooks enable incremental coding through cells with immediate feedback, but their linear structure and global namespace limit s…

cs.LG2020★ 2 cited

Supervised Whole DAG Causal Discovery

Hebi Li, Qi Xiao, Jin Tian

We propose to address the task of causal structure learning from data in a supervised manner. Existing work on learning causal directions by supervised learning is restricted to le…

cs.CL2020★ 1 cited

SueNes: A Weakly Supervised Approach to Evaluating Single-Document Summarization via Negative Sampling

Forrest Sheng Bao, Hebi Li, Ge Luo +4

Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical similarity which cannot well capture semantics nor linguistic quality and require a reference summar…

cs.LG2019★ 3 cited

Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders

Hebi Li, Qi Xiao, Shixin Tian +1

Machine learning models are vulnerable to adversarial examples. Iterative adversarial training has shown promising results against strong white-box attacks. However, adversarial tr…