4 papers
Feedback-Calibrated Protein Optimization with Batch-Aligned Tail Arbitration
Zefeng Lin, Xianyong Fang, Tianfan Fu +1
Protein optimization aims to discover high-fitness sequences under a limited experimental budget. Existing machine-learning methods use task-specific predictors, biological priors,…
RNA Design via Conditioned Flow Matching and Finite-Policy Reinforcement Learning
Zefeng Lin, Xianyong Fang, Tianfan Fu +1
RNA design aims to identify sequences that fold into specified secondary structures. Existing methods formulate the task as target-specific search or conditional generation. Howeve…
EnzyPGM: Pocket-conditioned Generative Model for Substrate-specific Enzyme Design
Zefeng Lin, Zhihang Zhang, Weirong Zhu +4
Designing enzymes with substrate-binding pockets is a critical challenge in protein engineering, as catalytic activity depends on the precise interaction between pockets and substr…
R: A LLM Based Novel-to-Screenplay Generation Framework with Causal Plot Graphs
Zefeng Lin, Yi Xiao, Zhiqiang Mo +8
Automatically adapting novels into screenplays is important for the TV, film, or opera industries to promote products with low costs. The strong performances of large language mode…