2 papers
cs.AI2026
CellWorld: From Gene-Level Reconstruction to Latent Cell Prediction in Spatial Transcriptomics Foundation Models
Haiping Liu, Qian Zhao, Lijing Lin +2
This paper shows that latent-space predictive pretraining can provide a scalable route to foundation models for spatial transcriptomics. Existing spatial transcriptomics foundation…
cs.LG2025
Rethinking RoPE: A Mathematical Blueprint for N-dimensional Positional Embedding
Haiping Liu, Lijing Lin, Jingyuan Sun +3
Rotary Position Embedding (RoPE) is widely adopted in large language models (LLMs) due to its efficient encoding of relative positions with strong extrapolation capabilities. Howev…