Search Results for author:
Found 68 papers, 39 papers with code
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
Large language models (LLMs) have shown remarkable performance in various natural language processing tasks.
HyperCLOVA X Technical Report
We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding.
Dense Text-to-Image Generation with Attention Modulation
To address this, we propose DenseDiffusion, a training-free method that adapts a pre-trained text-to-image model to handle such dense captions while offering control over the scene layout.
KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application
Large language models (LLMs) learn not only natural text generation abilities but also social biases against different demographic groups from real-world data.
SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration
The potential social harms that large language models pose, such as generating offensive content and reinforcing biases, are steeply rising.
Query-Efficient Black-Box Red Teaming via Bayesian Optimization
To this end, we propose Bayesian red teaming (BRT), novel query-efficient black-box red teaming methods based on Bayesian optimization, which iteratively identify diverse positive test cases leading to model failures by utilizing the pre-defined user input pool and the past evaluations.
Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models
Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding.
Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning
Recent studies have proposed unified user modeling frameworks that leverage user behavior data from various applications.
On Divergence Measures for Bayesian Pseudocoresets
Finally, we propose a novel Bayesian pseudocoreset algorithm based on minimizing forward KL divergence.
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models
To combine parameter-efficient adaptation and model compression, we propose AlphaTuning consisting of post-training quantization of the pre-trained language model and fine-tuning only some parts of quantized parameters for a target task.
Continuous Decomposition of Granularity for Neural Paraphrase Generation
While Transformers have had significant success in paragraph generation, they treat sentences as linear sequences of tokens and often neglect their hierarchical information.
Generator Knows What Discriminator Should Learn in Unconditional GANs
Here we explore the efficacy of dense supervision in unconditional generation and find generator feature maps can be an alternative of cost-expensive semantic label maps.
Time Is MattEr: Temporal Self-supervision for Video Transformers
Understanding temporal dynamics of video is an essential aspect of learning better video representations.
Deformable Graph Transformer
Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision.
Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
In this work, we propose a new evaluation metric, called `rarity score', to measure the individual rarity of each image synthesized by generative models.
Dataset Condensation via Efficient Synthetic-Data Parameterization
The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning.
Two-Step Question Retrieval for Open-Domain QA
These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models.
On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model
Many recent studies on large-scale language models have reported successful in-context zero- and few-shot learning ability.
Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries
A large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning scenarios under noisy data streams are yet underexplored.
Metropolis-Hastings Data Augmentation for Graph Neural Networks
We also propose a simple and effective semi-supervised learning strategy with generated samples from MH-Aug. Our extensive experiments demonstrate that MH-Aug can generate a sequence of samples according to the target distribution to significantly improve the performance of GNNs.
Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks
In this paper, we found that the recent emerging paradigm of implicit neural representations (INRs) that encodes a continuous signal into a parameterized neural network effectively mitigates the issue.
Ranked #25 on
Video Generation
on UCF-101
Contrastive Fine-grained Class Clustering via Generative Adversarial Networks
Specifically, we map the input of a generator, which was sampled from the categorical distribution, to the embedding space of the discriminator and let them act as a cluster centroid.
Scaling Law for Recommendation Models: Towards General-purpose User Representations
Here we explore the possibility of general-purpose user representation learning by training a universal user encoder at large scales.
Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference
For better practicality, we first propose a novel continual learning setup that is online, task-free, class-incremental, of blurry task boundaries and subject to inference queries at any moment.
Chameleon Sampling: Diverse and Pure Example Selection for Online Continual Learning with Noisy Labels
Specifically, we argue the importance of both diversity and purity of examples in the episodic memory of continual learning models.
What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers
GPT-3 shows remarkable in-context learning ability of large-scale language models (LMs) trained on hundreds of billion scale data.
Weakly Supervised Pre-Training for Multi-Hop Retriever
In multi-hop QA, answering complex questions entails iterative document retrieval for finding the missing entity of the question.
KLUE: Korean Language Understanding Evaluation
We introduce Korean Language Understanding Evaluation (KLUE) benchmark.
Reward Optimization for Neural Machine Translation with Learned Metrics
Results show that the reward optimization with BLEURT is able to increase the metric scores by a large margin, in contrast to limited gain when training with smoothed BLEU.
Rainbow Memory: Continual Learning with a Memory of Diverse Samples
Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial.
Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
Our method is learning to learn a primary task with various auxiliary tasks to improve generalization performance.
M2FN: Multi-step Modality Fusion for Advertisement Image Assessment
Assessing advertisements, specifically on the basis of user preferences and ad quality, is crucial to the marketing industry.
DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances
Recent advances in pre-trained language models have significantly improved neural response generation.
Context-Aware Answer Extraction in Question Answering
With experiments on reading comprehension, we show that BLANC outperforms the state-of-the-art QA models, and the performance gap increases as the number of answer text occurrences increases.
ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding
Language model pre-training has shown promising results in various downstream tasks.
Which Strategies Matter for Noisy Label Classification? Insight into Loss and Uncertainty
Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems.
Ranked #23 on
Image Classification
on Clothing1M
(using extra training data)
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
Our proposed method is learning to learn a primary task by predicting meta-paths as auxiliary tasks.
CareCall: a Call-Based Active Monitoring Dialog Agent for Managing COVID-19 Pandemic
Tracking suspected cases of COVID-19 is crucial to suppressing the spread of COVID-19 pandemic.
Boosting Active Learning for Speech Recognition with Noisy Pseudo-labeled Samples
The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models.
AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights
Because of the scale invariance, this modification only alters the effective step sizes without changing the effective update directions, thus enjoying the original convergence properties of GD optimizers.
Graphs, Entities, and Step Mixture
Existing approaches for graph neural networks commonly suffer from the oversmoothing issue, regardless of how neighborhoods are aggregated.
ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers
Automatic speech recognition (ASR) via call is essential for various applications, including AI for contact center (AICC) services.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Modeling Musical Onset Probabilities via Neural Distribution Learning
Musical onset detection can be formulated as a time-to-event (TTE) or time-since-event (TSE) prediction task by defining music as a sequence of onset events.
StarGAN v2: Diverse Image Synthesis for Multiple Domains
A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains.
Fundus to Angiography Generation
Multimodal Unsupervised Image-To-Image Translation
+1
NL2pSQL: Generating Pseudo-SQL Queries from Under-Specified Natural Language Questions
Here we describe a new NL2pSQL task to generate pSQL codes from natural language questions on under-specified database issues, NL2pSQL.
Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling
We first assume that the priors of future samples can be generated in an independently and identically distributed (i. i. d.)
Which Ads to Show? Advertisement Image Assessment with Auxiliary Information via Multi-step Modality Fusion
Despite crucial influences of image quality, auxiliary information of ad images such as tags and target subjects can also determine image preference.
Tripartite Heterogeneous Graph Propagation for Large-scale Social Recommendation
The oversmoothing of GNNs is an obstacle of GNN-based social recommendation as well.
ACE: Artificial Checkerboard Enhancer to Induce and Evade Adversarial Attacks
The checkerboard phenomenon is one of the well-known visual artifacts in the computer vision field.
Photorealistic Style Transfer via Wavelet Transforms
The key ingredient of our method is wavelet transforms that naturally fits in deep networks.
Phase-aware Speech Enhancement with Deep Complex U-Net
Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction.
Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation
Answerer in Questioner's Mind (AQM) is an information-theoretic framework that has been recently proposed for task-oriented dialog systems.
Multi-Domain Processing via Hybrid Denoising Networks for Speech Enhancement
We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task.
Audio and Speech Processing Sound
NSML: Meet the MLaaS platform with a real-world case study
The boom of deep learning induced many industries and academies to introduce machine learning based approaches into their concern, competitively.
CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms
Many hyperparameter optimization (HyperOpt) methods assume restricted computing resources and mainly focus on enhancing performance.
Neural Distribution Learning for generalized time-to-event prediction
Predicting the time to the next event is an important task in various domains.
DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling.
Reinforcement Learning based Recommender System using Biclustering Technique
A recommender system aims to recommend items that a user is interested in among many items.
Automatic Music Highlight Extraction using Convolutional Recurrent Attention Networks
Music highlights are valuable contents for music services.
NSML: A Machine Learning Platform That Enables You to Focus on Your Models
However, researchers are still required to perform a non-trivial amount of manual tasks such as GPU allocation, training status tracking, and comparison of models with different hyperparameter settings.
Highrisk Prediction from Electronic Medical Records via Deep Attention Networks
Predicting highrisk vascular diseases is a significant issue in the medical domain.
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model.
Ranked #1 on
Image-to-Image Translation
on RaFD
(using extra training data)
Representation Learning of Music Using Artist Labels
In this paper, we present a supervised feature learning approach using artist labels annotated in every single track as objective meta data.
Sound Audio and Speech Processing
Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning
Recommender systems aim to find an accurate and efficient mapping from historic data of user-preferred items to a new item that is to be liked by a user.
Overcoming Catastrophic Forgetting by Incremental Moment Matching
Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task.
Dual Attention Networks for Multimodal Reasoning and Matching
We propose Dual Attention Networks (DANs) which jointly leverage visual and textual attention mechanisms to capture fine-grained interplay between vision and language.
Ranked #2 on
Visual Question Answering (VQA)
on VQA v1 test-dev
Hadamard Product for Low-rank Bilinear Pooling
Bilinear models provide rich representations compared with linear models.
Multimodal Residual Learning for Visual QA
We present Multimodal Residual Networks (MRN) for the multimodal residual learning of visual question-answering, which extends the idea of the deep residual learning.
