Yuhui Zhang

VLMClassifier. Official implementation of "Why are Visually-Grounded Language Models Bad at Image Classification?" (NeurIPS 2024)

TransSeg. Official Code Release for "Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation" (ML4H 2022)

SogouWord. Python

CellFlux. Official implementation of "CellFlux: Simulating Cellular Morphology Changes via Flow Matching" (ICML 2025)

AutoConverter. Official implementation of "Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation" (CVPR 2025)

C3. Official implementation of "Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data" (ICLR 2024)

drml. Official Code Release for "Diagnosing and Rectifying Vision Models using Language" (ICLR 2023)

VetTag. Official Code Release for VetTag: improving automated veterinary diagnosis coding via large-scale language modeling

Minimal-Academic-Website. Minimal Academic Website Template

NeQA. Official Code Release for "Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models" (ACL 2023 Findings)

FactCCX. Python

MixedModalitySearch. Python

GPU-Smart. Interactive Automatic GPU Manager

SememeTransformer. Official Code Release for Enhancing Transformer with Sememe Knowledge

nlg_metrics. A unified framework for recent evaluation metrics about natural language generation.

CPU. C

USBVirus. Visual Basic

blip2_finetune. Jupyter Notebook

NegVQA. Official implementation of "NegVQA: Can Vision Language Models Understand Negation?" (ACL 2025 Findings)

MetaLearning. Python

vlm_mmlu. Python

LMRecSys. Official Code Release for Language Models as Recommender Systems: Evaluations and Limitations