Amrith Setlur
19 papers · 2020–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🗺️ Taxonomy Completionist (47) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
👑
Triple Crown
📈
Trend Setter
🗃️
Keyword Collector
(93)
🚀
Conference Pioneer
🔥
Unstoppable · Bronze
❓
The Questioner
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Machine Learning
(18)
Artificial Intelligence
(12)
Application Areas
(10)
Core AI
(8)
Optimization & Theory
(8)
Learning Types · Machine Learning
(7)
Core Methods
(6)
Deep Learning
(5)
Learning Paradigms
(4)
Learning Types · Deep Learning
(3)
Reinforcement Learning
(2)
Security & Privacy
(2)
Differential Privacy
(2)
Methods
(2)
Models
(2)
Keywords
distribution shift
(6)
large language model
(3)
spurious correlation
(3)
differential privacy
(2)
domain adaptation
(2)
reinforcement learning
(2)
test-time compute
(2)
fine tuning
(2)
transfer learning
(2)
image generation
(1)
contrastive learning
(1)
domain generalization
(1)
few-shot learning
(1)
feature learning
(1)
representation learning
(1)
text-to-image synthesis
(1)
style transfer
(1)
semi-supervised learning
(1)
kl divergence
(1)
feature selection
(1)
Papers
Optimizing Test-Time Compute via Meta Reinforcement Finetuning
ICML 2025
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
ICLR 2025
Scaling Test-Time Compute Without Verification or RL is Suboptimal
ICML 2025
What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning?
ICML 2025
Deep Neural Networks Tend To Extrapolate Predictably
ICLR 2024
On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
NeurIPS 2024
Private and Personalized Frequency Estimation in a Federated Setting
NeurIPS 2024
Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features
ICLR 2024
Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models
ICML 2024
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
NeurIPS 2024
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
ICLR 2023
Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift
NeurIPS 2023
Contextual Reliability: When Different Features Matter in Different Contexts
ICML 2023
Adversarial Unlearning: Reducing Confidence Along Adversarial Directions
NeurIPS 2022
Explaining the Efficacy of Counterfactually Augmented Data
ICLR 2021
Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution
NeurIPS 2021
Nonlinear ISA with Auxiliary Variables for Learning Speech Representations
Interspeech 2020
Politeness Transfer: A Tag and Generate Approach
ACL 2020
ReStGAN: A step towards visually guided shopper experience via text-to-image synthesis
WACV 2020