3 papers
cs.AI2026
When Do LLM Preferences Predict Downstream Behavior?
Katarina Slama, Alexandra Souly, Dishank Bansal +3
Preference-driven behavior in LLMs may be a necessary precondition for AI misalignment such as sandbagging: models cannot strategically pursue misaligned goals unless their behavio…
cs.LG2023
TaskMet: Task-Driven Metric Learning for Model Learning
Dishank Bansal, Ricky T. Q. Chen, Mustafa Mukadam +1
Deep learning models are often deployed in downstream tasks that the training procedure may not be aware of. For example, models solely trained to achieve accurate predictions may…
cs.CV2021
-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
Dhaivat Bhatt, Kaustubh Mani, Dishank Bansal +3
While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as sel…