Publications (32)
Artificial Intelligence Security Competition (AISC)
Yinpeng Dong, Peng Chen, Senyou Deng +49
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artifi…
Sketch2Manga: Shaded Manga Screening from Sketch with Diffusion Models
Jian Lin, Xueting Liu, Chengze Li +2
While manga is a popular entertainment form, creating manga is tedious, especially adding screentones to the created sketch, namely manga screening. Unfortunately, there is no exis…
MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization
Yangjia Hu, Haodong Wang, Zicong Hong +8
4-bit quantization significantly reduces the memory footprint and accelerates the inference of large language models (LLMs). However, its limited bit-width representation struggles…
See-through: Single-image Layer Decomposition for Anime Characters
Jian Lin, Chengze Li, Haoyun Qin +5
We introduce a framework that automates the transformation of static anime illustrations into manipulatable 2.5D models. Current professional workflows require tedious manual segme…
TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization
Haodong Wang, Junjie Liu, Zicong Hong +4
4-bit quantization reduces the memory footprint and latency of large language model inference, but its aggressive precision reduction can severely degrade accuracy. Prior methods a…
Efficient Preparation of Fermionic Superfluids in an Optical Dipole Trap through Reinforcement Learning
Yueyang Min, Ziliang Li, Yi Zhong +4
We demonstrate a reinforcement learning (RL) based control framework for optimizing evaporative cooling in the preparation of strongly interacting degenerate Fermi gases of Li6. Us…