collaborators

5 papers

cs.CV2026

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…

cs.CL2026

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.…

cs.LG2025

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…

cs.CV2025

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…

cs.CV2025

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…