TorchScale: Transformers at Scale

microsoft/torchscale 23 Nov 2022

Large Transformers have achieved state-of-the-art performance across many tasks.

Language Modelling Machine Translation +1

219
3.32 stars / hour

Human-level play in the game of Diplomacy by combining language models with strategic reasoning

facebookresearch/diplomacy_cicero Science 2022

Despite much progress in training AI systems to imitate human language, building agents that use language to communicate intentionally with humans in interactive environments remains a major challenge.

Language Modelling

459
3.05 stars / hour

DiffusionDet: Diffusion Model for Object Detection

shoufachen/diffusiondet 17 Nov 2022

In inference, the model refines a set of randomly generated boxes to the output results in a progressive way.

Denoising object-detection +1

1,210
2.68 stars / hour

AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities

flagai-open/flagai 12 Nov 2022

In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model.

Contrastive Learning Cross-Modal Retrieval +11

613
1.53 stars / hour

SinDiffusion: Learning a Diffusion Model from a Single Natural Image

weilunwang/sindiffusion 22 Nov 2022

We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image.

Denoising Image Generation +1

74
1.04 stars / hour

Galactica: A Large Language Model for Science

paperswithcode/galai 16 Nov 2022

We believe these results demonstrate the potential for language models as a new interface for science.

Classification Language Modelling +4

1,577
0.85 stars / hour

RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation

anciukevicius/renderdiffusion 17 Nov 2022

In this paper, we present RenderDiffusion as the first diffusion model for 3D generation and inference that can be trained using only monocular 2D supervision.

3D Reconstruction Image Denoising +3

109
0.83 stars / hour

EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

baaivision/eva 14 Nov 2022

We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data.

 Ranked #1 on Object Detection on LVIS v1.0 val (using extra training data)

Action Classification Action Recognition +6

203
0.75 stars / hour

Latent Video Diffusion Models for High-Fidelity Video Generation with Arbitrary Lengths

yingqinghe/lvdm 23 Nov 2022

Diffusion models (DMs) are another class of deep generative models and have recently achieved remarkable performance on various image synthesis tasks.

Denoising Image Generation +1

32
0.74 stars / hour