Umang Bhatt
15 papers · 2019–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Cross-Pollinator (10) π Academic Marathon (6) π§ Keyword Pioneer π Conference Polyglot (7) π Interdisciplinary Bridge
π
Conference Polyglot
(7)
π
Academic Marathon
(6)
π€
Dynamic Duo
(12)
π§¬
Topic Evolution
π
Century Club
(15)
β‘
Prolific Year
(5)
π
Conference Pioneer
ποΈ
Keyword Collector
(72)
π₯
Unstoppable
(7)
Conferences
AAAI (7)
IJCAI (2)
UAI (2)
AISTATS (1)
EMNLP (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
uncertainty quantification
(3)
conformal prediction
(2)
human-ai collaboration
(2)
model interpretability
(2)
feature attribution
(2)
feature importance
(2)
large language model
(2)
counterfactual explanation
(2)
uncertainty estimation
(2)
representation learning
(2)
variational inference
(1)
human-in-the-loop learning
(1)
concept representation
(1)
causal inference
(1)
policy learning
(1)
model calibration
(1)
few-shot learning
(1)
concept learning
(1)
statistical power
(1)
sensitivity analysis
(1)
Papers
Learning Personalized Decision Support Policies
AAAI 2025
Large Language Models Must Be Taught to Know What They Donβt Know
NIPS 2024
On the informativeness of supervision signals
UAI 2023
Approximating Full Conformal Prediction at Scale via Influence Functions
AAAI 2023
Towards Robust Metrics for Concept Representation Evaluation
AAAI 2023
Iterative Teaching by Data Hallucination
AISTATS 2023
Human-in-the-Loop Mixup
UAI 2023
On the Utility of Prediction Sets in Human-AI Teams
IJCAI 2022
Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis
EMNLP 2022
Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates
AAAI 2022
On the Fairness of Causal Algorithmic Recourse
AAAI 2022
FIMAP: Feature Importance by Minimal Adversarial Perturbation
AAAI 2021
Getting a CLUE: A Method for Explaining Uncertainty Estimates
ICLR 2021
Evaluating and Aggregating Feature-based Model Explanations
IJCAI 2020
Building Human-Machine Trust via Interpretability
AAAI 2019