Sadhika Malladi

9

Papers

267

Total Citations

Papers (9)

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws

Overtrained Language Models Are Harder to Fine-Tune

Trainable Transformer in Transformer

LESS: Selecting Influential Data for Targeted Instruction Tuning

On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)

NeurIPS 2021arXiv

On the SDEs and Scaling Rules for Adaptive Gradient Algorithms

NeurIPS 2022arXiv

Fine-Tuning Language Models with Just Forward Passes

NeurIPS 2023arXiv