Aditi Raghunathan

11

Papers

348

Total Citations

Papers (11)

Understanding Catastrophic Forgetting in Language Models via Implicit Inference

Dissecting Adversarial Robustness of Multimodal LM Agents

Scaling Laws for Data Filtering— Data Curation cannot be Compute Agnostic

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

Overtrained Language Models Are Harder to Fine-Tune

Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction

Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning

Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance

Reasoning as an Adaptive Defense for Safety

NeurIPS 2025arXiv

Repetition Improves Language Model Embeddings

Understanding Finetuning for Factual Knowledge Extraction