5 papers
An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation
Giang Son Nguyen, Zi Pong Lim, Sarthak Ketanbhai Modi +2
Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.g., Mermaid). In production, these systems…
Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding
Jianzhu Bao, Haozhen Zhang, Kuicai Dong +5
Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasingly large synthetic datasets.…
SOSAE: Self-Organizing Sparse AutoEncoder
Sarthak Ketanbhai Modi, Zi Pong Lim, Yushi Cao +3
The process of tuning the size of the hidden layers for autoencoders has the benefit of providing optimally compressed representations for the input data. However, such hyper-param…
Towards Universal & Efficient Model Compression via Exponential Torque Pruning
Sarthak Ketanbhai Modi, Zi Pong Lim, Shourya Kuchhal +5
The rapid growth in complexity and size of modern deep neural networks (DNNs) has increased challenges related to computational costs and memory usage, spurring a growing interest…
Towards Calibration Enhanced Network by Inverse Adversarial Attack
Yupeng Cheng, Zi Pong Lim, Sarthak Ketanbhai Modi +3
Test automation has become increasingly important as the complexity of both design and content in Human Machine Interface (HMI) software continues to grow. Current standard practic…