Aditi Raghunathan

S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations CVPR 2026 Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance ICLR 2025 Dissecting Adversarial Robustness of Multimodal LM Agents ICLR 2025 Memorization Sinks: Isolating Memorization during LLM Training ICML 2025 Mitigating Bias in RAG: Controlling the Embedder ACL 2025 Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions EMNLP 2025 On the Feasibility of In-Context Probing for Data Attribution NAACL 2025 Overtrained Language Models Are Harder to Fine-Tune ICML 2025 Repetition Improves Language Model Embeddings ICLR 2025 Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction ICML 2025 Scaling Laws for Precision ICLR 2025 Theory of Agreement-on-the-Line in Linear Models and Gaussian Data AISTATS 2025 Understanding the Influence of Synthetic Data for Text Embedders ACL 2025 Predicting the Performance of Foundation Models via Agreement-on-the-Line NeurIPS 2024 Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic CVPR 2024 Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning ICLR 2024 Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line NeurIPS 2024 T-MARS: Improving Visual Representations by Circumventing Text Feature Learning ICLR 2024 Understanding Catastrophic Forgetting in Language Models via Implicit Inference ICLR 2024 Understanding Finetuning for Factual Knowledge Extraction ICML 2024 Why is SAM Robust to Label Noise? ICLR 2024 Automatically Auditing Large Language Models via Discrete Optimization ICML 2023 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 Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models CVPR 2023 Using Language to Extend to Unseen Domains ICLR 2023 Agreement-on-the-line: Predicting the Performance of Neural Networks under Distribution Shift NeurIPS 2022 An Explanation of In-context Learning as Implicit Bayesian Inference ICLR 2022 Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift UAI 2022 Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution ICLR 2022 Learning Representations that Enable Generalization in Assistive Tasks CoRL 2022 Test Time Adaptation via Conjugate Pseudo-labels NeurIPS 2022 Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization ICML 2021 Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices ICML 2021 Just Train Twice: Improving Group Robustness without Training Group Information ICML 2021 An Investigation of Why Overparameterization Exacerbates Spurious Correlations ICML 2020 DROCC: Deep Robust One-Class Classification ICML 2020 Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming NeurIPS 2020 Robust Encodings: A Framework for Combating Adversarial Typos ACL 2020 The Pitfalls of Simplicity Bias in Neural Networks NeurIPS 2020 Understanding and Mitigating the Tradeoff between Robustness and Accuracy ICML 2020 Certified Robustness to Adversarial Word Substitutions EMNLP 2019 Unlabeled Data Improves Adversarial Robustness NeurIPS 2019 Certified Defenses against Adversarial Examples ICLR 2018 Semidefinite relaxations for certifying robustness to adversarial examples NeurIPS 2018 Estimating the unseen from multiple populations ICML 2017 Learning Mixture of Gaussians with Streaming Data NeurIPS 2017 Estimation from Indirect Supervision with Linear Moments ICML 2016