Papers by Xuye Liu

4 papers
NBDESCRIB: A Dataset for Text Description Generation from Tables and Code in Jupyter Notebooks with Guidelines (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for Jupyter Notebooks focus on generating cell-level descriptions from code snippets or table outputs independently.
Approach: They propose a task to generate personalized cell-level descriptions using code, tables, and user-written guidelines in Jupyter Notebooks.
Outcome: The proposed task combines code, tables, and user-written guidelines with personalized descriptions to evaluate the performance of existing models.
HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks (2021.findings-emnlp)

Copied to clipboard

Challenge: In computational notebooks, one documentation in a markdown cell often corresponds to multiple code cells, and these code cells have an inherent structure.
Approach: They propose a new task of code documentation generation for computational notebooks that uses hierarchical attention mechanism to consider code cells and code tokens information when generating documentation.
Outcome: The proposed model outperforms baseline models on a corpus constructed from well-documented Kaggle notebooks.
ELIOT: Zero-Shot Video-Text Retrieval through Relevance-Boosted Captioning and Structural Information Extraction (2025.naacl-srw)

Copied to clipboard

Challenge: Recent advances in video-text retrieval (VTR) have relied on supervised learning and fine-tuning.
Approach: They propose a zero-shot video-text retrieval framework that leverages off-the-shelf captioners, large language models, and text retrieval methods without additional training or annotated data.
Outcome: The proposed framework outperforms existing methods on video-text retrieval benchmarks without data.
BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors .
Approach: They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents.
Outcome: The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations