Search Results for author:
Found 4 papers, 1 papers with code
Mysterious Projections: Multimodal LLMs Gain Domain-Specific Visual Capabilities Without Richer Cross-Modal Projections
It is desirable to understand the roles of these two modules in modeling domain-specific visual attributes to inform the design of future models and streamline the interpretability efforts on the current models.
Predictive Churn with the Set of Good Models
And we characterize expected churn over model updates via the Rashomon set, pairing our analysis with empirical results on real-world datasets -- showing how our approach can be used to better anticipate, reduce, and avoid churn in consumer-facing applications.
Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraints
Along the way, we refine the study of single-target multiplicity by introducing notions of multiplicity that respect resource constraints -- a feature of many real-world tasks that is not captured by existing notions of predictive multiplicity.
Predictive Multiplicity in Probabilistic Classification
We demonstrate the incidence and prevalence of predictive multiplicity in real-world tasks.
