Tsvetomira Dumbalska

According to our database, Tsvetomira Dumbalska authored at least 4 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

AI Assistance Reduces Persistence and Hurts Independent Performance.

Grace Liu, Brian R. Christian, Tsvetomira Dumbalska, Michiel A. Bakker, Rachit Dubey

CoRR, April, 2026

Reward Models Inherit Value Biases from Pretraining.

Brian R. Christian, Jessica A. F. Thompson, Elle Michelle Yang, Vincent Adam, Hannah Rose Kirk, Christopher Summerfield, Tsvetomira Dumbalska

CoRR, January, 2026

2025

Reward Model Interpretability via Optimal and Pessimal Tokens.

Brian R. Christian, Hannah Rose Kirk, Jessica A. F. Thompson, Christopher Summerfield, Tsvetomira Dumbalska

Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025

2022

How do (perceptual) distracters distract?

Tsvetomira Dumbalska, Katarzyna Rudzka, Hannah E. Smithson, Christopher Summerfield

PLoS Comput. Biol., October, 2022