Gianluca M. Bencomo

According to our database, Gianluca M. Bencomo authored at least 5 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks.

Gianluca M. Bencomo, Max Gupta, Ioana Marinescu, R. Thomas McCoy, Thomas L. Griffiths

CoRR, February, 2025

Hindsight Merging: Diverse Data Generation with Language Models.

Veniamin Veselovsky, Benedikt Stroebl, Gianluca M. Bencomo, Dilip Arumugam, Lisa Schut, Arvind Narayanan, Thomas L. Griffiths

Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2025

2024

Using Contrastive Learning with Generative Similarity to Learn Spaces that Capture Human Inductive Biases.

Raja Marjieh, Sreejan Kumar, Declan Campbell, Liyi Zhang, Gianluca M. Bencomo, Jake Snell, Thomas L. Griffiths

CoRR, 2024

A Metalearned Neural Circuit for Nonparametric Bayesian Inference.

Jake Snell, Gianluca M. Bencomo, Tom Griffiths

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Implicit Maximum a Posteriori Filtering via Adaptive Optimization.

Gianluca M. Bencomo, Jake Snell, Thomas L. Griffiths

Proceedings of the Twelfth International Conference on Learning Representations, 2024