Papers by Jialin Wu

5 papers
CoNAN: A Complementary Neighboring-based Attention Network for Referring Expression Generation (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to identify and describe complex daily scenes are limited by ambiguity.
Approach: They propose a Complementary Neighboring-based Attention Network that utilizes visual differences between the target object and its highly-related neighbors as complementary features.
Outcome: The proposed expression outperforms state-of-the-art models on a dataset of 3D objects.
Convolutional LoRA Aggregation for Unseen Tasks Adaptation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing LoRA selection methods rely on a few task samples, making it difficult to capture full scope of task-relevant information.
Approach: They propose a framework that selects appropriate LoRA modules and aggregates them using a convolutional LoRA aggregator.
Outcome: The proposed framework bridges the knowledge gap between selected modules and target task . it ensures comprehensive coverage of task-relevant LoRA modules .
From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing vision-language models are based on exactmatch based accuracy and its derivations to evaluate performance.
Approach: They propose a toolkit that supports systematic benchmarking, analysis, and interpretation of vision-language models by extracting intermediate outputs from any layer during the forward pass of open-source VLMs.
Outcome: The proposed toolkit supports 16 state-of-the-art base VLMs and their over 30 variants and is extensible to accommodate new models without changing the core logic.
Entity-Focused Dense Passage Retrieval for Outside-Knowledge Visual Question Answering (2022.emnlp-main)

Copied to clipboard

Challenge: Existing outsideknowledge visual question answering systems lack retrieved knowledge and supervision is weak .
Approach: They propose an Entity-Focused Retrieval model that provides stronger supervision during training and recognizes question-relevant entities to help retrieve more specific knowledge.
Outcome: The proposed model achieves superior retrieval performance on the currently largest outside-knowledge VQA dataset.
Generating Question Relevant Captions to Aid Visual Question Answering (P19-1)

Copied to clipboard

Challenge: Visual question answering and image captioning require a shared body of general knowledge connecting language and vision.
Approach: They propose a method that exploits a shared body of general knowledge connecting language and vision by jointly generating captions.
Outcome: The proposed approach obtains state-of-the-art performance on the VQA v2 challenge . it uses human annotated captions to generate question-relevant captions .

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