3 citations · 9 across the 11 of their papers we have counts for
11 papers
Task-Aware Calibration: Provably Optimal Decoding in LLMs
Tim Tomov, Dominik Fuchsgruber, Rajeev Verma +1
LLM decoding often relies on the model's predictive distribution to generate an output. Consequently, misalignment with respect to the true generating distribution leads to subopti…
Incentive Aware AI Regulations: A Credal Characterisation
Anurag Singh, Julian Rodemann, Rajeev Verma +2
The rapid proliferation of AI applications has intensified debate on effective regulation of these black-box services. Effective regulation must balance two competing goals: (1) de…
Detecting Object Tracking Failure via Sequential Hypothesis Testing
Alejandro Monroy Muñoz, Rajeev Verma, Alexander Timans
Real-time online object tracking in videos constitutes a core task in computer vision, with wide-ranging applications including video surveillance, motion capture, and robotics. De…
Equity by Design? On the Trade-Offs in Fairness-Driven Recommendation in Heterogeneous Two-Sided Markets
Dominykas Seputis, Alexander Timans, Rajeev Verma
Two-sided marketplaces embody heterogeneity in incentives: producers seek exposure while consumers seek relevance, and balancing these competing objectives through constrained opti…
On Continuous Monitoring of Risk Violations under Unknown Shift
Alexander Timans, Rajeev Verma, Eric Nalisnick +1
Machine learning systems deployed in the real world must operate under dynamic and often unpredictable distribution shifts. This challenges the validity of statistical safety assur…
Read Your Own Mind: Reasoning Helps Surface Self-Confidence Signals in LLMs
Jakub Podolak, Rajeev Verma
We study the source of uncertainty in DeepSeek R1-32B by analyzing its self-reported verbal confidence on question answering (QA) tasks. In the default answer-then-confidence setti…
On Calibration in Multi-Distribution Learning
Rajeev Verma, Volker Fischer, Eric Nalisnick
Modern challenges of robustness, fairness, and decision-making in machine learning have led to the formulation of multi-distribution learning (MDL) frameworks in which a predictor…
Learning to Defer to a Population: A Meta-Learning Approach
Dharmesh Tailor, Aditya Patra, Rajeev Verma +2
The learning to defer (L2D) framework allows autonomous systems to be safe and robust by allocating difficult decisions to a human expert. All existing work on L2D assumes that eac…
Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles
Rajeev Verma, Daniel Barrejón, Eric Nalisnick
We study the statistical properties of learning to defer (L2D) to multiple experts. In particular, we address the open problems of deriving a consistent surrogate loss, confidence…
Calibrated Learning to Defer with One-vs-All Classifiers
Rajeev Verma, Eric Nalisnick
The learning to defer (L2D) framework has the potential to make AI systems safer. For a given input, the system can defer the decision to a human if the human is more likely than t…
An AI aid to the editors. Exploring the possibility of an AI assisted article classification system
Tirthankar Ghosal, Rajeev Verma, Asif Ekbal +2
This work is a preliminary exploratory study of how we could progress a step towards an AI assisted article classification sys- tem in academia. The proposed system aims to aid the…