Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Q-Steer: Action-Value Guidance for Molecular Policy Optimization
Xinyu Wang, Jinbo Bi, Minghu Song
Oracle-limited molecular optimization gives reward only after a complete molecule is generated, while each rollout requires many local next-token decisions. This delayed-feedback i…
cs.LG2026
SIGMA: Semantic Identifier Grouping for Molecular Autoregression
Xinyu Wang, Fei Dou, Jinbo Bi +1
Autoregressive molecular models assign probability to molecular serializations even though chemical identity is invariant to serialization. Equivalent serializations can therefore…
cs.LG2025
Leveraging Partial SMILES Validation Scheme for Enhanced Drug Design in Reinforcement Learning Frameworks
Xinyu Wang, Jinbo Bi, Minghu Song
SMILES-based molecule generation has emerged as a powerful approach in drug discovery. Deep reinforcement learning (RL) using large language model (LLM) has been incorporated into…