Search Results for author:
Found 25 papers, 15 papers with code
MTVG : Multi-text Video Generation with Text-to-Video Models
Concerning the characteristics of video, multi-text conditioning incorporating sequential events is necessary for next-step video generation.
Hexa: Self-Improving for Knowledge-Grounded Dialogue System
A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e. g., web-search, memory retrieval) with modular approaches.
Effortless Integration of Memory Management into Open-Domain Conversation Systems
Open-domain conversation systems integrate multiple conversation skills into a single system through a modular approach.
MAGVLT: Masked Generative Vision-and-Language Transformer
Particularly, MAGVLT achieves competitive results on both zero-shot image-to-text and text-to-image generation tasks from MS-COCO by one moderate-sized model (fewer than 500M parameters) even without the use of monomodal data and networks.
LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward
In order to resolve these issues, in this paper, we propose a learnable hash-based episodic count, which we name LECO, that efficiently performs as a task-specific intrinsic reward in hard exploration problems.
Selective Token Generation for Few-shot Natural Language Generation
Natural language modeling with limited training data is a challenging problem, and many algorithms make use of large-scale pretrained language models (PLMs) for this due to its great generalization ability.
Insights From the NeurIPS 2021 NetHack Challenge
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge.
Contrastive Regularization for Semi-Supervised Learning
Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high performance.
Selective Token Generation for Few-shot Language Modeling
Therefore, in this work, we develop a novel additive learning algorithm based on reinforcement learning (RL) for few-shot natural language generation (NLG) tasks.
Automated Learning Rate Scheduler for Large-batch Training
Large-batch training has been essential in leveraging large-scale datasets and models in deep learning.
Hybrid Generative-Contrastive Representation Learning
On the other hand, the generative pre-training directly estimates the data distribution, so the representations tend to be robust but not optimal for discriminative tasks.
Spatially Consistent Representation Learning
While these contrastive methods mainly focus on generating invariant global representations at the image-level under semantic-preserving transformations, they are prone to overlook spatial consistency of local representations and therefore have a limitation in pretraining for localization tasks such as object detection and instance segmentation.
Learning Loss for Test-Time Augmentation
Data augmentation has been actively studied for robust neural networks.
Visual Concept Reasoning Networks
It approximates sparsely connected networks by explicitly defining multiple branches to simultaneously learn representations with different visual concepts or properties.
AutoCLINT: The Winning Method in AutoCV Challenge 2019
NeurIPS 2019 AutoDL challenge is a series of six automated machine learning competitions.
torchgpipe: On-the-fly Pipeline Parallelism for Training Giant Models
We design and implement a ready-to-use library in PyTorch for performing micro-batch pipeline parallelism with checkpointing proposed by GPipe (Huang et al., 2019).
Spatially Attentive Output Layer for Image Classification
In this paper, we propose a novel spatial output layer on top of the existing convolutional feature maps to explicitly exploit the location-specific output information.
Mining GOLD Samples for Conditional GANs
Conditional generative adversarial networks (cGANs) have gained a considerable attention in recent years due to its class-wise controllability and superior quality for complex generation tasks.
Scalable Neural Architecture Search for 3D Medical Image Segmentation
In this paper, a neural architecture search (NAS) framework is proposed for 3D medical image segmentation, to automatically optimize a neural architecture from a large design space.
Edge-labeling Graph Neural Network for Few-shot Learning
In this paper, we propose a novel edge-labeling graph neural network (EGNN), which adapts a deep neural network on the edge-labeling graph, for few-shot learning.
Fast AutoAugment
Data augmentation is an essential technique for improving generalization ability of deep learning models.
Ranked #3 on
Image Classification
on SVHN
The Liver Tumor Segmentation Benchmark (LiTS)
In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018.
Bayesian Model-Agnostic Meta-Learning
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem.
A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
However, on new and challenging types of models our findings disagree and suggest that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.
Higher-Order Correlation Clustering for Image Segmentation
For many of the state-of-the-art computer vision algorithms, image segmentation is an important preprocessing step.
