3 citations · 11 across the 10 of their papers we have counts for
10 papers
Compositional Foundation Models for Hierarchical Planning
Anurag Ajay, Seungwook Han, Yilun Du +7
To make effective decisions in novel environments with long-horizon goals, it is crucial to engage in hierarchical reasoning across spatial and temporal scales. This entails planni…
Estimating the Density Ratio between Distributions with High Discrepancy using Multinomial Logistic Regression
Akash Srivastava, Seungwook Han, Kai Xu +2
Functions of the ratio of the densities are widely used in machine learning to quantify the discrepancy between the two distributions and . For high-dimensional distri…
Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies
Ligong Han, Seungwook Han, Shivchander Sudalairaj +8
Transformations based on domain expertise (expert transformations), such as random-resized-crop and color-jitter, have proven critical to the success of contrastive learning techni…
An Autonomous System for Head-to-Head Race: Design, Implementation and Analysis; Team KAIST at the Indy Autonomous Challenge
Chanyoung Jung, Andrea Finazzi, Hyunki Seong +6
While the majority of autonomous driving research has concentrated on everyday driving scenarios, further safety and performance improvements of autonomous vehicles require a focus…
Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries
Charlotte Loh, Seungwook Han, Shivchander Sudalairaj +5
Deep ensembles (DE) have been successful in improving model performance by learning diverse members via the stochasticity of random initialization. While recent works have attempte…
Design, Field Evaluation, and Traffic Analysis of a Competitive Autonomous Driving Model in a Congested Environment
Daegyu Lee, Hyunki Seong, Seungil Han +3
Recently, numerous studies have investigated cooperative traffic systems using the communication among vehicle-to-everything (V2X). Unfortunately, when multiple autonomous vehicles…
On the Importance of Calibration in Semi-supervised Learning
Charlotte Loh, Rumen Dangovski, Shivchander Sudalairaj +5
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency…
Equivariant Contrastive Learning
Rumen Dangovski, Li Jing, Charlotte Loh +5
In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations pres…
not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution
Seungwook Han, Akash Srivastava, Cole Hurwitz +2
State-of-the-art models for high-resolution image generation, such as BigGAN and VQVAE-2, require an incredible amount of compute resources and/or time (512 TPU-v3 cores) to train,…
PathGAN: Local Path Planning with Attentive Generative Adversarial Networks
Dooseop Choi, Seung-jun Han, Kyoungwook Min +1
To achieve autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our ge…