Papers by Pei Fu

4 papers
Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in vision-language models have unified perception and understanding tasks within Visual Question Answering paradigms.
Approach: They propose to outline timeline, architecture, and pipeline of nearly all TIU MLLMs and review their performance on mainstream benchmarks.
Outcome: The proposed models perform well on mainstream benchmarks and are compared with other models.
SciText2Eq: Assessing LLMs for Explainable Equation Generation for Scientific Creativity (2026.findings-acl)

Copied to clipboard

Challenge: Prior work has addressed problems in unstructured grounding, multi-equation dependency, and human-aligned evaluation.
Approach: They construct a dataset of scientific texts and evaluate it using an explainable equation generation workflow using automatic metrics and human judgments.
Outcome: The proposed model achieves moderate performance on lexical and syntactic similarity, but struggles with semantic accuracy.
Doc-V*: Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA (2026.acl-long)

Copied to clipboard

Challenge: Existing OCR-free approaches to document visual question answering are brittle and passive.
Approach: They propose an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
Outcome: The proposed framework outperforms open-source and proprietary models in five benchmarks and improves out-of-domain performance by 47.9% over baseline.
CAML: A Conflict-Aware Molecular Language Model Merging Framework for Multi-Constraint Molecular Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing paradigms struggle with this challenge due to catastrophic forgetting or gradient conflicts.
Approach: They propose a conflict-aware molecular language model merging framework that generates multiple constraints moleculaire as a cooperative game among property-specific fine-tune models.
Outcome: The proposed framework generates multiple constraints molecular as a cooperative game among property-specific fine-tune models (expert models) it minimizes conflicts among properties by exploring the optimal combination of the importance of the task parameter and relative fusion weights of each expert (fusion coefficient).

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