122 citations · 253 across the 25 of their papers we have counts for
26 papers
Greedy Local Learning for Language Model Pretraining: Gaps and Objective Design
Jihwan Moon, Sheir A. Zaheer, Jinmyoung Lee +2
Greedy block-wise local learning splits a network into gradient-isolated blocks trained by local auxiliary losses, deleting the backward pass between blocks: inter-stage communicat…
IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
Insu Jeon, Wonkwang Lee, Myeongjang Pyeon +1
We propose a new GAN-based unsupervised model for disentangled representation learning. The new model is discovered in an attempt to utilize the Information Bottleneck (IB) framewo…
Neural Variational Dropout Processes
Insu Jeon, Youngjin Park, Gunhee Kim
Learning to infer the conditional posterior model is a key step for robust meta-learning. This paper presents a new Bayesian meta-learning approach called Neural Variational Dropou…
Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models
Soochan Lee, Gunhee Kim
Generating intermediate steps, or Chain of Thought (CoT), is an effective way to significantly improve language models' (LM) multi-step reasoning capability. However, the CoT lengt…
KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application
Hwaran Lee, Seokhee Hong, Joonsuk Park +3
Large language models (LLMs) learn not only natural text generation abilities but also social biases against different demographic groups from real-world data. This poses a critica…
SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration
Hwaran Lee, Seokhee Hong, Joonsuk Park +10
The potential social harms that large language models pose, such as generating offensive content and reinforcing biases, are steeply rising. Existing works focus on coping with thi…
MPCHAT: Towards Multimodal Persona-Grounded Conversation
Jaewoo Ahn, Yeda Song, Sangdoo Yun +1
In order to build self-consistent personalized dialogue agents, previous research has mostly focused on textual persona that delivers personal facts or personalities. However, to f…
SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization
Hyunwoo Kim, Jack Hessel, Liwei Jiang +9
Data scarcity has been a long standing issue in the field of open-domain social dialogue. To quench this thirst, we present SODA: the first publicly available, million-scale high-q…
Multimodal Knowledge Alignment with Reinforcement Learning
Youngjae Yu, Jiwan Chung, Heeseung Yun +8
Large language models readily adapt to novel settings, even without task-specific training data. Can their zero-shot capacity be extended to multimodal inputs? In this work, we pro…
ProsocialDialog: A Prosocial Backbone for Conversational Agents
Hyunwoo Kim, Youngjae Yu, Liwei Jiang +5
Most existing dialogue systems fail to respond properly to potentially unsafe user utterances by either ignoring or passively agreeing with them. To address this issue, we introduc…
Lipschitz-constrained Unsupervised Skill Discovery
Seohong Park, Jongwook Choi, Jaekyeom Kim +2
We study the problem of unsupervised skill discovery, whose goal is to learn a set of diverse and useful skills with no external reward. There have been a number of skill discovery…
Unsupervised Representation Learning via Neural Activation Coding
Yookoon Park, Sangho Lee, Gunhee Kim +1
We present neural activation coding (NAC) as a novel approach for learning deep representations from unlabeled data for downstream applications. We argue that the deep encoder shou…
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods
Seohong Park, Jaekyeom Kim, Gunhee Kim
In reinforcement learning, continuous time is often discretized by a time scale , to which the resulting performance is known to be highly sensitive. In this work, we seek to fi…
Continual Learning on Noisy Data Streams via Self-Purified Replay
Chris Dongjoo Kim, Jinseo Jeong, Sangwoo Moon +1
Continually learning in the real world must overcome many challenges, among which noisy labels are a common and inevitable issue. In this work, we present a repla-ybased continual…
Pano-AVQA: Grounded Audio-Visual Question Answering on 360 Videos
Heeseung Yun, Youngjae Yu, Wonsuk Yang +2
360 videos convey holistic views for the surroundings of a scene. It provides audio-visual cues beyond pre-determined normal field of views and displays distinctive spatial…
Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes
Hyunwoo Kim, Byeongchang Kim, Gunhee Kim
Empathy is a complex cognitive ability based on the reasoning of others' affective states. In order to better understand others and express stronger empathy in dialogues, we argue…
On the Virality of Animated GIFs on Tumblr
Yunseok Jang, Yale Song, Gunhee Kim
Animated GIFs are becoming increasingly popular in online communication. People use them to express emotion, share their interests and enhance (or even replace) short-form texting;…
Cycled Compositional Learning between Images and Text
Jongseok Kim, Youngjae Yu, Seunghwan Lee +1
We present an approach named the Cycled Composition Network that can measure the semantic distance of the composition of image-text embedding. First, the Composition Network transi…
Unsupervised Skill Discovery with Bottleneck Option Learning
Jaekyeom Kim, Seohong Park, Gunhee Kim
Having the ability to acquire inherent skills from environments without any external rewards or supervision like humans is an important problem. We propose a novel unsupervised ski…
Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration
Jaekyeom Kim, Minjung Kim, Dongyeon Woo +1
We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only en…
ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning
Sangho Lee, Jiwan Chung, Youngjae Yu +4
The natural association between visual observations and their corresponding sound provides powerful self-supervisory signals for learning video representations, which makes the eve…
LID 2020: The Learning from Imperfect Data Challenge Results
Yunchao Wei, Shuai Zheng, Ming-Ming Cheng +32
Learning from imperfect data becomes an issue in many industrial applications after the research community has made profound progress in supervised learning from perfectly annotate…
Imbalanced Continual Learning with Partitioning Reservoir Sampling
Chris Dongjoo Kim, Jinseo Jeong, Gunhee Kim
Continual learning from a sequential stream of data is a crucial challenge for machine learning research. Most studies have been conducted on this topic under the single-label clas…
Augmenting Data for Sarcasm Detection with Unlabeled Conversation Context
Hankyol Lee, Youngjae Yu, Gunhee Kim
We present a novel data augmentation technique, CRA (Contextual Response Augmentation), which utilizes conversational context to generate meaningful samples for training. We also m…