Quantitative Methods

Sophie Kearney, Shu Yang, Zixuan Wen et al.

This work addresses accurate diagnosis of Alzheimer's disease for clinical applications, though it is incremental as it adapts existing LLM methods to a specific domain.

Tianyu Liu, Weihao Xuan, Hao Wu et al.

This addresses the challenge of building reliable AI copilots for real-world pathology scenarios, though it appears incremental as it builds on existing multimodal models with reinforcement learning enhancements.

Shu Quan, Tianfang Hao, Sitong Fang et al.

This work addresses a critical blind spot in LLM safety evaluation by providing a domain-specific benchmark and metric for biosecurity, which is important for AI safety researchers and policymakers, though it is domain-specific and incremental in methodology.

Shuizhou Chen, Lang Yu, Kedu Jin et al.

This work addresses inefficiencies and biological fidelity issues in virtual cell models for computational biology, representing a domain-specific advancement.

Edward De Brouwer, Carl Edwards, Alexander Wu et al.

Provides the first standard benchmark for in silico phenotypic screening, a key capability for virtual cell models in drug discovery.

Andrew Shen, Shaul Druckmann, James Zou

For AI-driven scientific discovery, AR provides a method to overcome LLM mode collapse, enabling more creative and effective solution generation in biomedicine.

Jon-Paul Cacioli

This reveals a limitation in transformers for modeling biological magnitude systems, showing distributional learning alone is insufficient to produce scalar variability.

Yanting Li, Zhuoyang Jiang, Enyan Dai et al.

This work addresses the challenge of reconciling conflicting objectives in molecular generation for drug discovery, offering a unified framework that improves multi-objective optimization.

Stefaan Simon Pierre Hessmann, Khaled Kahouli, Stefan Gugler et al.

GPFFs provide a fast, accurate, and training-data-efficient method for molecular generation, enabling real-time drug design applications.

Lukas Fesser, Hanlin Zhang, Michelle M. Li et al.

This work provides a systematic understanding of post-training effects for practitioners building biological reasoning models, revealing non-monotonic performance gains and trade-offs.

Xinrui Chen, Yizhen Luo, Siqi Fan et al.

This work addresses the challenge of designing functional proteins without evolutionary templates, benefiting biotechnology and medicine by improving both functionality and foldability.

Raghav Kansal, David Crair, Nghia Nguyen et al.

This work addresses the problem of learning dynamic transport maps with intermediate constraints, which is crucial for modeling temporal evolution in scientific domains.

Zongru Li, Xingsheng Chen, Honggang Wen et al.

For researchers in cheminformatics and drug discovery, this provides a comprehensive taxonomy and benchmark analysis, but is largely a survey with no new methods or results.

Chuang Zhao, Hongke Zhao, Xiaofang Zhou et al.

This work improves clinical reasoning for healthcare applications by enabling models to better internalize complex case nuances, though it appears incremental as it builds on existing test-time training and calibration methods.

Zhenyu Wang, Geyan Ye, Wei Liu et al.

This work addresses the need for more reliable and interpretable virtual cell perturbation predictions for biological mechanism studies, representing a domain-specific advancement.

Yehui Yang, Zelin Zang, Changxi Chi et al.

This addresses the challenge of generalizing to out-of-distribution cell states in single-cell annotation, offering a robust solution for biological research.

Yixuan Yang, Mehak Arora, Ryan Zhang et al.

This work addresses the challenge of obtaining a unified pretrained model for EHR that simultaneously handles forecasting and diverse risk-prediction tasks, which is important for clinical decision support.

Dejun Lin, Simon Chu, Vishanth Iyer et al.

This addresses the problem of scaling biomolecular modeling for researchers by providing a scalable pathway to model massive systems, representing an incremental improvement in computational efficiency.

Zane Koch, Asmamaw T. Wassie, Javier Valdes-Aleman et al.

This work addresses the problem of systematically evaluating AI agents on complex, multi-step computational biology tasks, which is crucial for scientists aiming to automate research workflows. It provides a new benchmark for the AI agent community.

Han Zhang, Guo-Hua Yuan, Chaohao Yuan et al.

This work provides a generative cellular world model for in silico simulation of cell states and perturbation responses, addressing the need for virtual cells in biological discovery and perturbation screening.