4.3k citations · 8.6k across the 159 of their papers we have counts for
26 papers · 1 filter
One-Step Diffusion Distillation via Deep Equilibrium Models
Zhengyang Geng, Ashwini Pokle, J. Zico Kolter
Diffusion models excel at producing high-quality samples but naively require hundreds of iterations, prompting multiple attempts to distill the generation process into a faster net…
Deep Equilibrium Based Neural Operators for Steady-State PDEs
Tanya Marwah, Ashwini Pokle, J. Zico Kolter +3
Data-driven machine learning approaches are being increasingly used to solve partial differential equations (PDEs). They have shown particularly striking successes when training an…
Manifold Preserving Guided Diffusion
Yutong He, Naoki Murata, Chieh-Hsin Lai +8
Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose M…
Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning
Melrose Roderick, Gaurav Manek, Felix Berkenkamp +1
A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the lear…
TorchDEQ: A Library for Deep Equilibrium Models
Zhengyang Geng, J. Zico Kolter
Deep Equilibrium (DEQ) Models, an emerging class of implicit models that maps inputs to fixed points of neural networks, are of growing interest in the deep learning community. How…
On the Neural Tangent Kernel of Equilibrium Models
Zhili Feng, J. Zico Kolter
This work studies the neural tangent kernel (NTK) of the deep equilibrium (DEQ) model, a practical ``infinite-depth'' architecture which directly computes the infinite-depth limit…
Understanding prompt engineering may not require rethinking generalization
Victor Akinwande, Yiding Jiang, Dylan Sam +1
Zero-shot learning in prompted vision-language models, the practice of crafting prompts to build classifiers without an explicit training process, has achieved impressive 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…
Can Neural Network Memorization Be Localized?
Pratyush Maini, Michael C. Mozer, Hanie Sedghi +3
Recent efforts at explaining the interplay of memorization and generalization in deep overparametrized networks have posited that neural networks "hard" example…
Monotone deep Boltzmann machines
Zhili Feng, Ezra Winston, J. Zico Kolter
Deep Boltzmann machines (DBMs), one of the first ``deep'' learning methods ever studied, are multi-layered probabilistic models governed by a pairwise energy function that describe…
Universal and Transferable Adversarial Attacks on Aligned Language Models
Andy Zou, Zifan Wang, Nicholas Carlini +3
Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to pr…
Text Descriptions are Compressive and Invariant Representations for Visual Learning
Zhili Feng, Anna Bair, J. Zico Kolter
Modern image classification is based upon directly predicting classes via large discriminative networks, which do not directly contain information about the intuitive visual featur…
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…
Localized Text-to-Image Generation for Free via Cross Attention Control
Yutong He, Ruslan Salakhutdinov, J. Zico Kolter
Despite the tremendous success in text-to-image generative models, localized text-to-image generation (that is, generating objects or features at specific locations in an image whi…
Language models are weak learners
Hariharan Manikandan, Yiding Jiang, J Zico Kolter
A central notion in practical and theoretical machine learning is that of a , classifiers that achieve better-than-random performance (on any given distribut…
On the Importance of Exploration for Generalization in Reinforcement Learning
Yiding Jiang, J. Zico Kolter, Roberta Raileanu
Existing approaches for improving generalization in deep reinforcement learning (RL) have mostly focused on representation learning, neglecting RL-specific aspects such as explorat…
On the Joint Interaction of Models, Data, and Features
Yiding Jiang, Christina Baek, J. Zico Kolter
Learning features from data is one of the defining characteristics of deep learning, but our theoretical understanding of the role features play in deep learning is still rudimenta…
A Simple and Effective Pruning Approach for Large Language Models
Mingjie Sun, Zhuang Liu, Anna Bair +1
As their size increases, Large Languages Models (LLMs) are natural candidates for network pruning methods: approaches that drop a subset of network weights while striving to preser…
Neural Functional Transformers
Allan Zhou, Kaien Yang, Yiding Jiang +5
The recent success of neural networks as implicit representation of data has driven growing interest in neural functionals: models that can process other neural networks as input b…
Mimetic Initialization of Self-Attention Layers
Asher Trockman, J. Zico Kolter
It is notoriously difficult to train Transformers on small datasets; typically, large pre-trained models are instead used as the starting point. We explore the weights of such pre-…
The Update-Equivalence Framework for Decision-Time Planning
Samuel Sokota, Gabriele Farina, David J. Wu +4
The process of revising (or constructing) a policy at execution time -- known as decision-time planning -- has been key to achieving superhuman performance in perfect-information g…
Sinkhorn-Flow: Predicting Probability Mass Flow in Dynamical Systems Using Optimal Transport
Mukul Bhutani, J. Zico Kolter
Predicting how distributions over discrete variables vary over time is a common task in time series forecasting. But whereas most approaches focus on merely predicting the distribu…
Learning with Explanation Constraints
Rattana Pukdee, Dylan Sam, J. Zico Kolter +2
As larger deep learning models are hard to interpret, there has been a recent focus on generating explanations of these black-box models. In contrast, we may have apriori explanati…
Model-tuning Via Prompts Makes NLP Models Adversarially Robust
Mrigank Raman, Pratyush Maini, J. Zico Kolter +2
In recent years, NLP practitioners have converged on the following practice: (i) import an off-the-shelf pretrained (masked) language model; (ii) append a multilayer perceptron ato…