Umang Bhatt

Identifiers

• name variant Umang Bhatt 0.60 · backfill

Papers (49)

1. Characterizing initial human-AI proof formalization workflows cs.AI · 2026 · author #12
2. Learning to Orchestrate Agents under Uncertainty cs.LG · 2026 · author #6
3. RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies cs.CY · 2026 · author #9
4. Measuring and mitigating overreliance to build human-compatible AI cs.CY · 2025 · author #17
5. Documenting Deployment with Fabric: A Repository of Real-World AI Governance cs.CY · 2025 · author #13
6. Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI cs.CY · 2025 · author #5
7. When Should We Orchestrate Multiple Agents? cs.MA · 2025 · author #1
8. Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems cs.LG · 2025 · author #6
9. Revisiting Rogers' Paradox in the Context of Human-AI Interaction cs.AI · 2025 · author #2
10. Building Machines that Learn and Think with People cs.HC · 2024 · author #3
11. Modulating Language Model Experiences through Frictions cs.HC · 2024 · author #9
12. Large Language Models Must Be Taught to Know What They Don't Know cs.LG · 2024 · author #6
13. Representational Alignment Supports Effective Machine Teaching cs.LG · 2024 · author #8
14. Towards interactive evaluations for interaction harms in human-AI systems cs.CY · 2024 · author #3
15. When Should Algorithms Resign? A Proposal for AI Governance cs.CY · 2024 · author #1
16. Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction cs.AI · 2024 · author #6
17. FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines cs.HC · 2023 · author #9
18. Selective Concept Models: Permitting Stakeholder Customisation at Test-Time cs.HC · 2023 · author #5
19. Evaluating Language Models for Mathematics through Interactions cs.LG · 2023 · author #6
20. Learning Personalized Decision Support Policies cs.LG · 2023 · author #1
21. Human Uncertainty in Concept-Based AI Systems cs.HC · 2023 · author #5
22. Harms from Increasingly Agentic Algorithmic Systems cs.CY · 2023 · author #19
23. Towards Robust Metrics for Concept Representation Evaluation cs.LG · 2023 · author #5
24. On the Informativeness of Supervision Signals cs.LG · 2022 · author #7
25. Human-in-the-Loop Mixup cs.LG · 2022 · author #2
26. Iterative Teaching by Data Hallucination cs.LG · 2022 · author #5
27. Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis cs.CL · 2022 · author #3
28. Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users cs.LG · 2022 · author #6
29. Eliciting and Learning with Soft Labels from Every Annotator cs.LG · 2022 · author #2
30. Perspectives on Incorporating Expert Feedback into Model Updates cs.LG · 2022 · author #2
31. On the Utility of Prediction Sets in Human-AI Teams cs.AI · 2022 · author #2
32. Approximating Full Conformal Prediction at Scale via Influence Functions cs.LG · 2022 · author #2
33. Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates cs.LG · 2021 · author #2
34. DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement cs.LG · 2021 · author #1
35. Do Concept Bottleneck Models Learn as Intended? cs.LG · 2021 · author #3
36. {\delta}-CLUE: Diverse Sets of Explanations for Uncertainty Estimates cs.LG · 2021 · author #2
37. A Multistakeholder Approach Towards Evaluating AI Transparency Mechanisms cs.HC · 2021 · author #3
38. Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty cs.CY · 2020 · author #1
39. On the Fairness of Causal Algorithmic Recourse cs.LG · 2020 · author #3
40. Machine Learning Explainability for External Stakeholders cs.CY · 2020 · author #1
41. Getting a CLUE: A Method for Explaining Uncertainty Estimates stat.ML · 2020 · author #2
42. Evaluating and Aggregating Feature-based Model Explanations cs.LG · 2020 · author #1
43. A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game cs.HC · 2019 · author #3
44. Explainable Machine Learning in Deployment cs.LG · 2019 · author #1
45. On Network Science and Mutual Information for Explaining Deep Neural Networks cs.LG · 2019 · author #2
46. Towards Aggregating Weighted Feature Attributions cs.LG · 2019 · author #1
47. The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting cs.HC · 2018 · author #2
48. Maintaining The Humanity of Our Models cs.CY · 2017 · author #1
49. Intelligent Pothole Detection and Road Condition Assessment cs.CY · 2017 · author #1

Mentions

• 2508.14119 #13 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2207.02726 #6 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2406.08391 #6 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2508.07872 #5 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2405.10632 #3 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2502.18635 #6 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2503.13577 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2406.04302 #8 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2304.06701 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2501.10476 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2407.12804 #9 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2408.03943 #3 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2402.18326 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2402.03618 #6 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2306.01694 #6 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2301.10367 #5 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2211.01202 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2307.15475 #9 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2211.01407 #7 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2306.08424 #5 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2302.10329 #19 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2210.17467 #5 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2303.12872 #5 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2202.01315 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2210.04714 #3 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2207.00810 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2205.06905 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2205.01411 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2010.06529 #3 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2112.02646 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2104.06323 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2107.05978 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2103.14976 #3 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2105.04289 #3 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2011.07586 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2006.06848 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2007.05408 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 1909.06342 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 1901.08557 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2005.00631 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 1910.11459 #3 · arxiv_oai · confidence 0.70 Umang Bhatt
• 1901.10040 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 1806.03671 #2 · arxiv_oai · confidence 0.70 Umang Bhatt
• 1711.05791 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 1710.02595 #1 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2606.04273 #12 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2605.27073 #6 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2603.11001 #9 · arxiv_oai · confidence 0.70 Umang Bhatt
• 2509.08010 #17 · arxiv_oai · confidence 0.70 Umang Bhatt

Frequent Coauthors

• Adrian Weller 32 shared papers
• Katherine M. Collins 16 shared papers
• Ilia Sucholutsky 10 shared papers
• Valerie Chen 6 shared papers
• Alice Xiang 5 shared papers
• Ameet Talwalkar 4 shared papers
• Joshua B. Tenenbaum 4 shared papers
• Mateja Jamnik 4 shared papers
• Matthew Barker 4 shared papers
• Thomas L. Griffiths 4 shared papers
• Holli Sargeant 3 shared papers
• Jos\'e M. F. Moura 3 shared papers
• Lujain Ibrahim 3 shared papers
• Q. Vera Liao 3 shared papers
• Weiyang Liu 3 shared papers
• Aaron M. Roth 2 shared papers
• Afsaneh Doryab 2 shared papers
• Ana Lucic 2 shared papers
• Andrew Gordon Wilson 2 shared papers
• Ankur Taly 2 shared papers