← Authors

Aditi Raghunathan

49 papers · 2016–2025 · 11 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (11) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (73) 🌈 Renaissance Researcher (8) 🐝 Cross-Pollinator (14) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer πŸƒ Academic Marathon (9) 🌟 Keyword Trendsetter Combo (3) πŸ‘‘ Triple Crown 🀝 Dynamic Duo (16) πŸš€ Conference Pioneer ⚑ Prolific Year (8) πŸ’Ž Century Club (49) πŸ—ƒοΈ Keyword Collector (149) ❓ The Questioner πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (10)

Conferences

ICML (14) ICLR (13) NIPS (10) ACL (3) CVPR (2) EMNLP (2) AISTATS (1) CORL (1) IJCNLP (1) NAACL (1) UAI (1)

Top co-authors

Percy Liang (16) Sachin Goyal (7) Jacob Mitchell Springer (6) Christina Baek (6) J. Zico Kolter (4) J Zico Kolter (4) Jacob Steinhardt (4) Ananya Kumar (3) Graham Neubig (3) Chelsea Finn (3)

Research topics

Optimization (1)

Keywords

distribution shift (7) out-of-distribution generalization (5) adversarial robustness (4) adversarial training (3) neural network (3) spurious correlation (3) contrastive learning (3) certified robustness (3) scaling law (2) convex relaxation (2) model selection (2) test-time adaptation (2) interval bound propagation (2) semidefinite programming (2) semi-supervised learning (2) parameter estimation (2) domain adaptation (2) ensemble learning (2) sentiment analysis (2) natural language inference (2)

Papers

Mitigating Bias in RAG: Controlling the Embedder ACL 2025
Understanding the Influence of Synthetic Data for Text Embedders ACL 2025
Theory of Agreement-on-the-Line in Linear Models and Gaussian Data AISTATS 2025
Memorization Sinks: Isolating Memorization during LLM Training ICML 2025
Repetition Improves Language Model Embeddings ICLR 2025
Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions EMNLP 2025
Overtrained Language Models Are Harder to Fine-Tune ICML 2025
On the Feasibility of In-Context Probing for Data Attribution NAACL 2025
Dissecting Adversarial Robustness of Multimodal LM Agents ICLR 2025
Scaling Laws for Precision ICLR 2025
Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction ICML 2025
Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance ICLR 2025
Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning ICLR 2024
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning ICLR 2024
Predicting the Performance of Foundation Models via Agreement-on-the-Line NIPS 2024
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line NIPS 2024
Understanding Finetuning for Factual Knowledge Extraction ICML 2024
Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic CVPR 2024
Why is SAM Robust to Label Noise? ICLR 2024
Understanding Catastrophic Forgetting in Language Models via Implicit Inference ICLR 2024
Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models CVPR 2023
Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift NIPS 2023
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts ICLR 2023
Using Language to Extend to Unseen Domains ICLR 2023
Automatically Auditing Large Language Models via Discrete Optimization ICML 2023
Contextual Reliability: When Different Features Matter in Different Contexts ICML 2023
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift UAI 2022
Test Time Adaptation via Conjugate Pseudo-labels NIPS 2022
Agreement-on-the-line: Predicting the Performance of Neural Networks under Distribution Shift NIPS 2022
Learning Representations that Enable Generalization in Assistive Tasks CORL 2022
An Explanation of In-context Learning as Implicit Bayesian Inference ICLR 2022
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution ICLR 2022
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices ICML 2021
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization ICML 2021
Just Train Twice: Improving Group Robustness without Training Group Information ICML 2021
Understanding and Mitigating the Tradeoff between Robustness and Accuracy ICML 2020
An Investigation of Why Overparameterization Exacerbates Spurious Correlations ICML 2020
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming NIPS 2020
The Pitfalls of Simplicity Bias in Neural Networks NIPS 2020
Robust Encodings: A Framework for Combating Adversarial Typos ACL 2020
DROCC: Deep Robust One-Class Classification ICML 2020
Unlabeled Data Improves Adversarial Robustness NIPS 2019
Certified Robustness to Adversarial Word Substitutions EMNLP 2019
Certified Robustness to Adversarial Word Substitutions IJCNLP 2019
Semidefinite relaxations for certifying robustness to adversarial examples NIPS 2018
Certified Defenses against Adversarial Examples ICLR 2018
Learning Mixture of Gaussians with Streaming Data NIPS 2017
Estimating the unseen from multiple populations ICML 2017
Estimation from Indirect Supervision with Linear Moments ICML 2016