6 papers
Alignment Risks from Capability-Seeking RL Training
Yujun Zhou, Yue Huang, Han Bao +8
While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerabl…
Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Models
Brenda Nogueira, Gisela A. Gonzalez-Montiel, Nitesh V. Chawla +1
Developing effective anticancer therapeutics remains challenging due to tumor heterogeneity and the absence of well-defined molecular targets across cancer subtypes. Generative mod…
SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression
Brenda Nogueira, Gisela A. Gonzalez-Montiel, Meng Jiang +2
Molecular property regression struggles with cases in chemically relevant target ranges that are underrepresented in datasets. Standard average error minimization approaches underp…
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Yue Huang, Yu Jiang, Wenjie Wang +12
Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate sh…
From Verification Burden to Trusted Collaboration: Design Goals for LLM-Assisted Literature Reviews
Brenda Nogueira, Werner Geyer, Andrew Anderson +4
Large Language Models (LLMs) are increasingly embedded in academic writing practices. Although numerous studies have explored how researchers employ these tools for scientific writ…
Spectral Manifold Harmonization for Graph Imbalanced Regression
Brenda Nogueira, Gabe Gomes, Meng Jiang +2
Graph-structured data is ubiquitous in scientific domains, where models often face imbalanced learning settings. In imbalanced regression, domain preferences focus on specific targ…