Qingyang Wu
2 papers · Latest:
Machine Learning
Search Your Block Floating Point Scales!
ScaleSearch optimizes Block Floating Point quantization scales by searching for minimal error, significantly improving generative model performance.
2605.12464
Computer VisionVisual Instruction Tuning
This paper introduces LLaVA, a large multimodal model trained via GPT-4-generated visual instruction data, achieving strong zero-shot visual-language understanding and state-of-the-art results on Science QA.
2304.08485
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.