Papers by Zilin Yu

4 papers
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Copied to clipboard

Challenge: Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach: AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome: Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (D18-1)

Copied to clipboard

Challenge: Existing datasets for semantic parsing are too small in terms of number of programs for training modern data-intensive models.
Approach: They propose a large-scale complex and cross-domain semantic parsing task for a database . they use a dataset with 10,181 questions and 5,693 unique complex SQL queries .
Outcome: The proposed task is different from previous tasks because it uses the same database and program . the best model achieves only 9.7% exact matching accuracy on a database split setting.
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to training document conversion models with manual annotation are costly and time-consuming, and training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications.
Approach: They propose a fully automated framework for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts.
Outcome: The proposed model outperforms existing models and improves on annotated documents.
TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation (N18-2)

Copied to clipboard

Challenge: Existing systems that can understand natural language questions and generate corresponding SQL queries are not able to do this.
Approach: They propose a novel approach which formats the problem as a slot filling task in a more reasonable way and utilizes type information to better understand rare entities and numbers in the questions.
Outcome: The proposed approach outperforms the prior art on the WikiSQL dataset and can reach 82.6% accuracy, a 17.5% improvement compared to the previous content-sensitive model.

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