arXiv subjects

Hebi Li

Publications and source records attributed to Hebi Li.

6 recordsLinked to original sources

arXiv2025

Kernel-FFI: Transparent Foreign Function Interfaces for Interactive Notebooks

Foreign Function Interfaces (FFIs) are essential for enabling interoperability between programming languages, yet existing FFI solutions are ill-suited for the dynamic, interactive workflows prevalent in modern notebook environments such as Jupyter. Current approaches require extensive manual configuration, introduce significant boilerplate, and often lack support for recursive calls and object-oriented programming (OOP) constructs-features critical for productive, multi-language development. We present Kernel-FFI, a transparent, language-agnostic framework that enables seamless cross-language function calls and object manipulation within interactive notebooks. Kernel-FFI employs source-level transformation to automatically rewrite cross-language invocations, eliminating the need for manual bindings or boilerplate. Kernel-FFI provides robust support for OOP by enabling foreign object referencing and automatic resource management across language boundaries. Furthermore, to address the blocking nature of Jupyter kernels and support recursive and asynchronous foreign calls, we introduce a novel side-channel communication mechanism. Our tool will be open-sourced and available at https://codepod.io/docs/kernel-ffi

cs.PL↗

arXiv2023

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

Interactive development environments like Jupyter Notebooks enable incremental coding through cells with immediate feedback, but their linear structure and global namespace limit scalability for large software projects. We present CodePod, a hierarchical extension of Jupyter that introduces a novel scoped execution model with formal semantics. Our key contribution is a language-agnostic runtime system that performs source-level transformations to implement hierarchical scoping rules, enabling true incremental evaluation across nested modules without requiring language-specific kernel modifications. We formalize the scoping semantics as a mathematical framework with precise visibility relations and prove key properties including uniqueness of symbol resolution and correctness of the resolution algorithm. A qualitative user study with seven senior developers demonstrates that CodePod enables significant improvements in project scalability compared to Jupyter, with notable reductions in navigation effort. We validate the system's effectiveness on large-scale projects with thousands of lines of code, demonstrating its applicability beyond traditional notebook boundaries. Our tool is open-source and available at https://codepod.io

cs.SE↗

arXiv2022

DocAsRef: An Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely

Automated summary quality assessment falls into two categories: reference-based and reference-free. Reference-based metrics, historically deemed more accurate due to the additional information provided by human-written references, are limited by their reliance on human input. In this paper, we hypothesize that the comparison methodologies used by some reference-based metrics to evaluate a system summary against its corresponding reference can be effectively adapted to assess it against its source document, thereby transforming these metrics into reference-free ones. Experimental results support this hypothesis. After being repurposed reference-freely, the zero-shot BERTScore using the pretrained DeBERTa-large-MNLI model of <0.5B parameters consistently outperforms its original reference-based version across various aspects on the SummEval and Newsroom datasets. It also excels in comparison to most existing reference-free metrics and closely competes with zero-shot summary evaluators based on GPT-3.5.

cs.AI↗

arXiv2020

Supervised Whole DAG Causal Discovery

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 learning pairwise relation, and not well suited for whole DAG discovery. We propose a novel approach of modeling the whole DAG structure discovery as a supervised learning. To fit the problem in hand, we propose to use permutation equivariant models that align well with the problem domain. We evaluate the proposed approach extensively on synthetic graphs of size 10,20,50,100 and real data, and show promising results compared with a variety of previous approaches.

cs.LG↗

arXiv2020

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

Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical similarity which cannot well capture semantics nor linguistic quality and require a reference summary which is costly to obtain. Recently, there have been a growing number of efforts to alleviate either or both of the two drawbacks. In this paper, we present a proof-of-concept study to a weakly supervised summary evaluation approach without the presence of reference summaries. Massive data in existing summarization datasets are transformed for training by pairing documents with corrupted reference summaries. In cross-domain tests, our strategy outperforms baselines with promising improvements, and show a great advantage in gauging linguistic qualities over all metrics.

cs.CL↗

arXiv2019

Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders

Machine learning models are vulnerable to adversarial examples. Iterative adversarial training has shown promising results against strong white-box attacks. However, adversarial training is very expensive, and every time a model needs to be protected, such expensive training scheme needs to be performed. In this paper, we propose to apply iterative adversarial training scheme to an external auto-encoder, which once trained can be used to protect other models directly. We empirically show that our model outperforms other purifying-based methods against white-box attacks, and transfers well to directly protect other base models with different architectures.

cs.LG↗