Hyochan Chong
d7chong
AI & ML interests
research engineer at samsung research | interested in model compression, ml systems
Recent Activity
authored
a paper
about 2 hours ago
NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
upvoted
a
paper
about 5 hours ago
RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs
submitted
a paper
about 5 hours ago
RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs
Organizations
None yet