Author

David Alvarez-Melis

h-index 7 View on Semantic Scholar

We have 3 of 29 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jul 2025

Can Interpretation Predict Behavior on Unseen Data?

This work proposes and demonstrates an alternate objective for a new interpretability objective: understanding model internals to predict behavior and assess reliability under distribution shift, and successfully uses attention patterns to predict which rule each model follows on OOD data.

Victoria R. Li, Jenny Kaufmann, Tian Qin et al. · arXiv.org · 13 citations · ⚡1

#machine learning Preprint Sep 2026

Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics

Wasserstein curriculum paths is presented, a simple transport-based framework that decouples factors by representing curricula as trajectories of training distributions over discrete difficulty levels and improves hard-level performance relative to exposure-matched static sampling.

Chang-Ho Shin, David Alvarez-Melis · 0 citations

Jul 2026

Bridging Compute- and Data-Optimal Pretraining

Compute-Data (CD) scaling laws are proposed, a unified framework that bridges compute-optimal scaling, where data scales freely with compute, and data-optimal scaling, where the corpus is fixed while compute can grow without bound.

Tian Qin, K. Hamidieh, David Alvarez-Melis · arXiv.org · 0 citations