5 papers
Toward Human-AI Complementarity Across Diverse Tasks
Yuzheng Xu, Annya Dahmani, Matthew D. Blanchard +13
Human-AI complementarity, the idea that combining human and AI judgments can outperform either alone, offers a promising pathway toward robust oversight of advanced AI systems. How…
Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling
Niclas Dern, Lennart Redl, Sebastian Pfister +3
Sampling from unnormalized target distributions, e.g.\ Boltzmann distributions , is fundamental to many scientific applications yet comp…
Theoretical Limitations of Ensembles in the Age of Overparameterization
Niclas Dern, John P. Cunningham, Geoff Pleiss
Classic ensembles generalize better than any single component model. In contrast, recent empirical studies find that modern ensembles of (overparameterized) neural networks may not…
Targeted Sequential Indirect Experiment Design
Elisabeth Ailer, Niclas Dern, Jason Hartford +1
Scientific hypotheses typically concern specific aspects of complex, imperfectly understood or entirely unknown mechanisms, such as the effect of gene expression levels on phenotyp…
Sumformer: Universal Approximation for Efficient Transformers
Silas Alberti, Niclas Dern, Laura Thesing +1
Natural language processing (NLP) made an impressive jump with the introduction of Transformers. ChatGPT is one of the most famous examples, changing the perception of the possibil…