# Controlling Style in Generated Dialogue

22 Sep 2020

Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters.

7,979
0.46 stars / hour

# Wizard of Wikipedia: Knowledge-Powered Conversational agents

In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date.

7,981
0.44 stars / hour

# Neural Fixed-Point Acceleration for Convex Optimization

21 Jul 2021

We present neural fixed-point acceleration, a framework to automatically learn to accelerate convex fixed-point problems that are drawn from a distribution, using ideas from meta-learning and classical acceleration algorithms.

20
0.42 stars / hour

# Diffusion Models Beat GANs on Image Synthesis

11 May 2021

Finally, we find that classifier guidance combines well with upsampling diffusion models, further improving FID to 3. 94 on ImageNet 256$\times$256 and 3. 85 on ImageNet 512$\times$512.

Ranked #1 on Image Generation on ImageNet 64x64 (FID metric)

611
0.41 stars / hour

# ReSSL: Relational Self-Supervised Learning with Weak Augmentation

20 Jul 2021

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations.

14
0.41 stars / hour

# Unsupervised Discovery of Object Radiance Fields

16 Jul 2021

We study the problem of inferring an object-centric scene representation from a single image, aiming to derive a representation that explains the image formation process, captures the scene's 3D nature, and is learned without supervision.

45
0.40 stars / hour

# DOBF: A Deobfuscation Pre-Training Objective for Programming Languages

15 Feb 2021

Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks.

30
0.40 stars / hour

# Towards Real-World Blind Face Restoration with Generative Facial Prior

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details.

802
0.40 stars / hour

# Per-Pixel Classification is Not All You Need for Semantic Segmentation

13 Jul 2021

Overall, the proposed mask classification-based method simplifies the landscape of effective approaches to semantic and panoptic segmentation tasks and shows excellent empirical results.

477
0.38 stars / hour

# Just Ask: Learning to Answer Questions from Millions of Narrated Videos

1 Dec 2020

In this work, we propose to avoid manual annotation and generate a large-scale training dataset for video question answering making use of automatic cross-modal supervision.

Ranked #1 on Visual Question Answering on MSVD-QA (using extra training data)

18
0.38 stars / hour