This work presents CellScientist, a protocol-constrained workflow that converts execution and validation feedback into auditable model-revision trajectories, and produces both a selected predictor and an inspectable record of its development.
Meng-Ran Li, Bo Li, Jia-Yi Wang et al.· 0 citations
ASECT improves over its backbone on three external pathology benchmarks covering classification and question answering beyond cellular composition tasks, and improves over its backbone on three external pathology benchmarks covering classification and question answering beyond cellular composition tasks.
Cheng-Yang Zhang, Wen-Chuan Zhang, Bo Li et al.· 0 citations
It is shown that cellular perturbation atlases can instead become reinforcement-learning environments, where measured gene responses provide computable rewards for biological reasoning, and introduces PertMind, which combines trusted-trajectory supervised initialization with gene-, pathway-, and format-level reinforcem...
Zhen-Chao Tang, Xiao-Gang Xu, Jia-Fei Wu et al.· 0 citations
AI virtual cells aim to predict cellular responses to specified interventions, yet held-out predictive performance alone does not establish use of the supplied perturbation information. This prediction-claim gap matters in agentic model discovery, where language-model agents generate and revise predictors using score-b...
Meng-Ran Li, Bo Li, Cheng-Yang Zhang et al.· 0 citations
Mul‐PheG2P outperforms existing methods across diverse crop datasets, and provides a multi‐scale interpretability chain: at the macro level, it quantifies phenotypic contributions via attention‐based weighting; at the micro level, Integrated Gradients reveal the genetic basis of predictions.
Jia-Hui Wang, Yong Zhang, Bo Li et al.· New Phytologist· 0 citations
Results show that current pathology VLMs still exhibit a substantial gap between answer-side performance and visual-semantic binding, and this work presents PathBind, a benchmark comprising 2,600 samples that undergoes task-specific automated filtering and expert review to reduce textual shortcuts and improve entity-re...
Cheng-Yang Zhang, Wen-Chuan Zhang, Bo Li et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.