Search Results for author:
Found 11 papers, 5 papers with code
Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models
This highly compressed representation of an image provides much more detailed guidance compared to latent representations of language and this significantly reduces the computational requirements to achieve state-of-the-art results.
Controllable Image Generation via Collage Representations
Our experiments on the OI dataset show that M&Ms outperforms baselines in terms of fine-grained scene controllability while being very competitive in terms of image quality and sample diversity.
Reinforced active learning for image segmentation
Our method proposes a new modification of the deep Q-network (DQN) formulation for active learning, adapting it to the large-scale nature of semantic segmentation problems.
Learning Sparse Mixture of Experts for Visual Question Answering
We aim to tackle this issue for the specific task of Visual Question Answering (VQA).
Structure Learning for Neural Module Networks
In current formulations of such networks only the parameters of the neural modules and/or the order of their execution is learned.
Active Domain Randomization
Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters.
Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents
Further, critical states in which a very high or a very low reward can be achieved are often interesting to understand the situational awareness of the system as they can correspond to risky states.
Visual Imitation Learning with Recurrent Siamese Networks
In this paper we propose an approach using only visual information to learn a distance metric between agent behaviour and a given video demonstration.
Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
In this work, we present a simple, effective multi-task learning framework for sentence representations that combines the inductive biases of diverse training objectives in a single model.
Ranked #1 on
Semantic Textual Similarity
on SentEval
Deep Complex Networks
Despite their attractive properties and potential for opening up entirely new neural architectures, complex-valued deep neural networks have been marginalized due to the absence of the building blocks required to design such models.
Ranked #3 on
Music Transcription
on MusicNet
A New Smooth Approximation to the Zero One Loss with a Probabilistic Interpretation
We examine a new form of smooth approximation to the zero one loss in which learning is performed using a reformulation of the widely used logistic function.
