Papers by Quanjun Yin

5 papers
MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for Referring Expression Comprehension (REC) lack specific domain abilities for precise local visual perception and visual-language alignment.
Approach: They propose a framework for Parameter-Efficient Transfer Learning to localize a visual region via natural language using a prior-guided prior.
Outcome: The proposed framework achieves the best accuracy compared to the current methods with only 1.41% tunable backbone parameters.
PychoAgent: Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events (2025.emnlp-main)

Copied to clipboard

Challenge: Social media's rich information content and spatiotemporal granularity provide unique opportunities for emotion prediction and management.
Approach: They propose a Psychology-driven generative Agent framework for explainable panic prediction based on emotion arousal theory.
Outcome: The proposed framework improves panic emotion prediction performance by 13% to 21% compared to baseline models.
CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on indoor or street settings, overlooking challenges of open-ended urban spaces.
Approach: They propose a benchmark to probe cross-view spatial reasoning capabilities of current VLMs in urban settings.
Outcome: The citycube benchmark examines the performance of current vision-language models in urban environments.
Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration (2021.emnlp-main)

Copied to clipboard

Challenge: Current models are not satisfactory for solving out-of-vocabulary problems . current models assume that the task ontology is well defined in advance .
Approach: They propose to enhance the interrelation between slots with masked hierarchical attention.
Outcome: The proposed model yields a significant performance gain over current state-of-the-art model and is more robust to out-ofvocabulary problem compared with other methods.
Learn to Relax with Large Language Models: Solving Constraint Optimization Problems via Bidirectional Coevolution (2026.acl-long)

Copied to clipboard

Challenge: Large Language Model (LLM)-based optimization has shown promise for autonomous problem solving, but most approaches cast LLMs as passive constraint checkers rather than proactive strategy designers.
Approach: They propose an end-to-end Automated Constraint Optimization method that tightly couples operations-research principles of constraint relaxation with LLM reasoning.
Outcome: Extensive experiments on three challenging COP benchmarks validate AutoCO’s consistent effectiveness and superior performance, especially in hard regimes where current methods degrade.

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