activity
20162025
most citedFine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

160 citations · 461 across the 27 of their papers we have counts for

collaborators
Showing cs.LGShow all

29 papers · 1 filter

cs.LG2025

Weight Ensembling Improves Reasoning in Language Models

Xingyu Dang, Christina Baek, Kaiyue Wen +2

We investigate a failure mode that arises during the training of reasoning models, where the diversity of generations begins to collapse, leading to suboptimal test-time scaling. N…

cs.LG2024

Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance

Sachin Goyal, Christina Baek, J. Zico Kolter +1

A standard practice when using large language models is for users to supplement their instruction with an input context containing new information for the model to process. However…

cs.LG2024

Why is SAM Robust to Label Noise?

Christina Baek, Zico Kolter, Aditi Raghunathan

Sharpness-Aware Minimization (SAM) is most known for achieving state-of the-art performances on natural image and language tasks. However, its most pronounced improvements (of tens…

cs.LG2024★ 1 cited

Predicting the Performance of Foundation Models via Agreement-on-the-Line

Rahul Saxena, Taeyoun Kim, Aman Mehra +3

Estimating the out-of-distribution performance in regimes where labels are scarce is critical to safely deploy foundation models. Recently, it was shown that ensembles of neural ne…

cs.LG2024★ 1 cited

AutoFT: Learning an Objective for Robust Fine-Tuning

Caroline Choi, Yoonho Lee, Annie Chen +3

Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. However, fine-tuning a model on one data distribution often degrades performan…

cs.LG2023★ 1 cited

Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line

Eungyeup Kim, Mingjie Sun, Christina Baek +2

Recently, Miller et al. (2021) and Baek et al. (2022) empirically demonstrated strong linear correlations between in-distribution (ID) versus out-of-distribution (OOD) accuracy and…