500AI
← People

Zhihang Yuan

Source-listed: Senior Engineer; lead of a multimodal large language model efficiency team · ByteDance

  • Language models
  • Efficient ML

Selected work

5
  1. LLM-ViewerMaintainer
  2. PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationFirst author · 2022
  3. RPTQ: Reorder-based Post-training Quantization for Large Language ModelsFirst author · 2023
  4. PB-LLM: Partially Binarized Large Language ModelsContributor · 2024
  5. ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language ModelsFirst author · 2023