Papers by Xuye Liu
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
Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Sahel Sharifymoghaddam, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Hosna Oyarhoseini, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin
| 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. |