Papers by Chang Chu

5 papers
PDFMathTranslate: Scientific Document Translation Preserving Layouts (2025.emnlp-demos)

Copied to clipboard

Challenge: Prior efforts in translating scientific documents overlooked layouts . PDFMathTranslate is open-source with more than 222k downloads - a record for the first time ever.
Approach: They propose PDFMathTranslate, the world's first open-source software for translating scientific documents while preserving layouts.
Outcome: The work is open-sourced at https://github.com/byaidu/pdfmathtranslate with more than 222k downloads.
Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation (2022.acl-long)

Copied to clipboard

Challenge: Existing studies focus on contrastive learning on the instance level without discriminating the contribution of each word.
Approach: They propose a hierarchical contrastive learning mechanism which can unify semantic meaning in the input text.
Outcome: The proposed model outperforms baselines on storytelling, paraphrasing, dialogue generation, and storytelling tasks.
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for audio-centric interaction have impeded advancements in this field . AIR-Bench evaluates LALMs' ability to understand audio signals and interact with humans .
Approach: They propose a benchmark to evaluate the ability of large audio-language models to understand audio signals . they use 19 tasks with approximately 19k single-choice questions to examine single-task ability .
Outcome: The proposed framework evaluates the ability of large audio-language models to understand audio signals and interact with humans in the textual format.
Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to multimodal speech emotion recognition and sentiment analysis have not improved results due to their relatively simple fusion mechanisms and lack of proper cross-modal pretraining.
Approach: They propose a deep-fused audio-text bi-modal transformer with carefully designed cross-modal fusion mechanism and stage-wise cross-mod pretraining scheme to facilitate cross-modulation.
Outcome: The proposed method exceeds benchmarks on public IEMOCAP emotion and CMU-MOSEI sentiment datasets by a large margin.
Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research (2025.findings-emnlp)

Copied to clipboard

Challenge: a rapid advancement of perovskite solar cells has led to an exponential growth in research publications.
Approach: They propose a knowledge-enhanced system for perovskite solar cells that integrates three key components.
Outcome: The proposed system outperforms existing models in domain-specific knowledge retrieval and scientific reasoning tasks.

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