This framework maps perturbation-driven cell-state evolution as continuous trajectories and represents unseen perturbations using prior-knowledge embeddings and improves distributional fidelity and predicts responses to held-out perturbation combinations.
Hee-Sun Choi, Gaeun Byeon, Hayoon Park et al.· bioRxiv· 0 citations
Real-world molecular design remains challenging for large language model (LLM)-based agents. It requires them to interpret design contexts, satisfy multiple constraints, identify infeasible specifications, and reason over multi-step tool outputs. Existing benchmarks do not capture this complexity, focusing instead on e...
Yongjun Jeong, Hanbum Ko, Yejun Kim et al.· 0 citations
Experimental results show that RetroReasoner outperforms prior baselines, including not only molecular LLMs but also retrosynthesis-specific expert models, and generates a broader range of feasible reactant proposals, especially for challenging reaction instances.
Hanbum Ko, Chanhui Lee, Yejun Kim et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.