2.3k citations · 3.9k across the 40 of their papers we have counts for
41 papers
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…
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…
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…
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…
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…
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…
Understanding Catastrophic Forgetting in Language Models via Implicit Inference
Suhas Kotha, Jacob Mitchell Springer, Aditi Raghunathan
We lack a systematic understanding of the effects of fine-tuning (via methods such as instruction-tuning or reinforcement learning from human feedback), particularly on tasks outsi…
Contextual Reliability: When Different Features Matter in Different Contexts
Gaurav Ghosal, Amrith Setlur, Daniel S. Brown +2
Deep neural networks often fail catastrophically by relying on spurious correlations. Most prior work assumes a clear dichotomy into spurious and reliable features; however, this i…
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
Pratyush Maini, Sachin Goyal, Zachary C. Lipton +2
Large web-sourced multimodal datasets have powered a slew of new methods for learning general-purpose visual representations, advancing the state of the art in computer vision and…
ALP: Action-Aware Embodied Learning for Perception
Xinran Liang, Anthony Han, Wilson Yan +2
Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong perfor…
Automatically Auditing Large Language Models via Discrete Optimization
Erik Jones, Anca Dragan, Aditi Raghunathan +1
Auditing large language models for unexpected behaviors is critical to preempt catastrophic deployments, yet remains challenging. In this work, we cast auditing as an optimization…
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
Amrith Setlur, Don Dennis, Benjamin Eysenbach +4
Training machine learning models robust to distribution shifts is critical for real-world applications. Some robust training algorithms (e.g., Group DRO) specialize to group shifts…
Learning Representations that Enable Generalization in Assistive Tasks
Jerry Zhi-Yang He, Aditi Raghunathan, Daniel S. Brown +2
Recent work in sim2real has successfully enabled robots to act in physical environments by training in simulation with a diverse ''population'' of environments (i.e. domain randomi…
Finetune like you pretrain: Improved finetuning of zero-shot vision models
Sachin Goyal, Ananya Kumar, Sankalp Garg +2
Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kuma…
Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding
William Chen, Siyi Hu, Rajat Talak +1
Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of a…
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift
Ananya Kumar, Tengyu Ma, Percy Liang +1
We often see undesirable tradeoffs in robust machine learning where out-of-distribution (OOD) accuracy is at odds with in-distribution (ID) accuracy: a robust classifier obtained v…
Test-Time Adaptation via Conjugate Pseudo-labels
Sachin Goyal, Mingjie Sun, Aditi Raghunathan +1
Test-time adaptation (TTA) refers to adapting neural networks to distribution shifts, with access to only the unlabeled test samples from the new domain at test-time. Prior TTA met…
Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift
Christina Baek, Yiding Jiang, Aditi Raghunathan +1
Recently, Miller et al. showed that a model's in-distribution (ID) accuracy has a strong linear correlation with its out-of-distribution (OOD) accuracy on several OOD benchmarks --…
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
Ananya Kumar, Aditi Raghunathan, Robbie Jones +2
When transferring a pretrained model to a downstream task, two popular methods are full fine-tuning (updating all the model parameters) and linear probing (updating only the last l…
An Explanation of In-context Learning as Implicit Bayesian Inference
Sang Michael Xie, Aditi Raghunathan, Percy Liang +1
Large language models (LMs) such as GPT-3 have the surprising ability to do in-context learning, where the model learns to do a downstream task simply by conditioning on a prompt c…
On the Opportunities and Risks of Foundation Models
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.…
Just Train Twice: Improving Group Robustness without Training Group Information
Evan Zheran Liu, Behzad Haghgoo, Annie S. Chen +5
Standard training via empirical risk minimization (ERM) can produce models that achieve high accuracy on average but low accuracy on certain groups, especially in the presence of s…
Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
John Miller, Rohan Taori, Aditi Raghunathan +6
For machine learning systems to be reliable, we must understand their performance in unseen, out-of-distribution environments. In this paper, we empirically show that out-of-distri…
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin +8
Convex relaxations have emerged as a promising approach for verifying desirable properties of neural networks like robustness to adversarial perturbations. Widely used Linear Progr…