2.2k citations · 10.8k across the 93 of their papers we have counts for
44 papers · 1 filter
Guide Your Agent with Adaptive Multimodal Rewards
Changyeon Kim, Younggyo Seo, Hao Liu +4
Developing an agent capable of adapting to unseen environments remains a difficult challenge in imitation learning. This work presents Adaptive Return-conditioned Policy (ARP), an…
3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation
Sungjun Cho, Dae-Woong Jeong, Sung Moon Ko +5
Pretraining molecular representations from large unlabeled data is essential for molecular property prediction due to the high cost of obtaining ground-truth labels. While there ex…
Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching
Byoungjip Kim, Sungik Choi, Dasol Hwang +2
Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources.…
Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
Sungmin Cha, Sungjun Cho, Dasol Hwang +3
Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sen…
Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders
Jongseong Jang, Daeun Kyung, Seung Hwan Kim +3
Deep neural networks are increasingly used in medical imaging for tasks such as pathological classification, but they face challenges due to the scarcity of high-quality, expert-la…
Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost
Sungjun Cho, Seonwoo Min, Jinwoo Kim +3
To overcome the quadratic cost of self-attention, recent works have proposed various sparse attention modules, most of which fall under one of two groups: 1) sparse attention under…
Improving Transferability of Representations via Augmentation-Aware Self-Supervision
Hankook Lee, Kibok Lee, Kimin Lee +2
Recent unsupervised representation learning methods have shown to be effective in a range of vision tasks by learning representations invariant to data augmentations such as random…
A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity
Seo Taek Kong, Soomin Jeon, Dongbin Na +3
Deep learning (DL) algorithms rely on massive amounts of labeled data. Semi-supervised learning (SSL) and active learning (AL) aim to reduce this label complexity by leveraging unl…
Adversarial Environment Generation for Learning to Navigate the Web
Izzeddin Gur, Natasha Jaques, Kevin Malta +3
Learning to autonomously navigate the web is a difficult sequential decision making task. The state and action spaces are large and combinatorial in nature, and websites are dynami…
State Entropy Maximization with Random Encoders for Efficient Exploration
Younggyo Seo, Lili Chen, Jinwoo Shin +3
Recent exploration methods have proven to be a recipe for improving sample-efficiency in deep reinforcement learning (RL). However, efficient exploration in high-dimensional observ…
Evolving Reinforcement Learning Algorithms
John D. Co-Reyes, Yingjie Miao, Daiyi Peng +5
We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-…
Few-shot Sequence Learning with Transformers
Lajanugen Logeswaran, Ann Lee, Myle Ott +3
Few-shot algorithms aim at learning new tasks provided only a handful of training examples. In this work we investigate few-shot learning in the setting where the data points are s…
Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning
Guangxiang Zhu, Minghao Zhang, Honglak Lee +1
Sample efficiency has been one of the major challenges for deep reinforcement learning. Recently, model-based reinforcement learning has been proposed to address this challenge by…
Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment
Wilka Carvalho, Anthony Liang, Kimin Lee +4
First-person object-interaction tasks in high-fidelity, 3D, simulated environments such as the AI2Thor virtual home-environment pose significant sample-efficiency challenges for re…
i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
Kibok Lee, Yian Zhu, Kihyuk Sohn +3
Contrastive representation learning has shown to be effective to learn representations from unlabeled data. However, much progress has been made in vision domains relying on data a…
Predictive Information Accelerates Learning in RL
Kuang-Huei Lee, Ian Fischer, Anthony Liu +4
The Predictive Information is the mutual information between the past and the future, I(X_past; X_future). We hypothesize that capturing the predictive information is useful in RL,…
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning
Kimin Lee, Younggyo Seo, Seunghyun Lee +2
Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global…
An Ode to an ODE
Krzysztof Choromanski, Jared Quincy Davis, Valerii Likhosherstov +6
We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the orthogonal group O(d…
Time Dependence in Non-Autonomous Neural ODEs
Jared Quincy Davis, Krzysztof Choromanski, Jake Varley +6
Neural Ordinary Differential Equations (ODEs) are elegant reinterpretations of deep networks where continuous time can replace the discrete notion of depth, ODE solvers perform for…
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
Sungryull Sohn, Hyunjae Woo, Jongwook Choi +1
We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph which describes a set of subtasks and their dependencies that are unknown to th…
Efficient Adversarial Training with Transferable Adversarial Examples
Haizhong Zheng, Ziqi Zhang, Juncheng Gu +2
Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require or…
Consistency Regularization for Generative Adversarial Networks
Han Zhang, Zizhao Zhang, Augustus Odena +1
Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have bee…
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
Kimin Lee, Kibok Lee, Jinwoo Shin +1
Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dim…
Distilling Effective Supervision from Severe Label Noise
Zizhao Zhang, Han Zhang, Sercan O. Arik +2
Collecting large-scale data with clean labels for supervised training of neural networks is practically challenging. Although noisy labels are usually cheap to acquire, existing me…