Catherine Cheng
chengyun01
ยท
AI & ML interests
large language models, vision-language models, multimodal machine learning, representation learning, continued pretraining, model distillation
Recent Activity
upvoted a paper about 10 hours ago
Contextual Drag: How Errors in the Context Affect LLM Reasoning authored a paper about 1 year ago
Multimodal Learning Without Labeled Multimodal Data: Guarantees and
Applications authored a paper about 1 year ago
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate
Modality Imbalance in VLMs?Organizations
