Controlling Style in Generated Dialogue

facebookresearch/ParlAI 22 Sep 2020

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

Dialogue Generation

7,979
0.46 stars / hour

Wizard of Wikipedia: Knowledge-Powered Conversational agents

facebookresearch/ParlAI ICLR 2019

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

Dialogue Generation

7,981
0.44 stars / hour

Neural Fixed-Point Acceleration for Convex Optimization

facebookresearch/neural-scs 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.

Meta-Learning

20
0.42 stars / hour

Diffusion Models Beat GANs on Image Synthesis

openai/guided-diffusion 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)

Image Generation

611
0.41 stars / hour

ReSSL: Relational Self-Supervised Learning with Weak Augmentation

KyleZheng1997/ReSSL 20 Jul 2021

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

Contrastive Learning Self-Supervised Learning

14
0.41 stars / hour

Unsupervised Discovery of Object Radiance Fields

KovenYu/uORF 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.

Novel View Synthesis Scene Segmentation

45
0.40 stars / hour

DOBF: A Deobfuscation Pre-Training Objective for Programming Languages

facebookresearch/CodeGen 15 Feb 2021

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

Code Search Language Modelling +1

30
0.40 stars / hour

Towards Real-World Blind Face Restoration with Generative Facial Prior

TencentARC/GFPGAN CVPR 2021

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

Blind Face Restoration GAN inversion

802
0.40 stars / hour

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

facebookresearch/MaskFormer 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.

Panoptic Segmentation

477
0.38 stars / hour

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

antoyang/just-ask 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)

Question Answering Question Generation +3

18
0.38 stars / hour