OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning

rui-ye/openfedllm 10 Feb 2024

Trained on massive publicly available data, large language models (LLMs) have demonstrated tremendous success across various fields.

Federated Learning Instruction Following +1

149
1.22 stars / hour

GraphCast: Learning skillful medium-range global weather forecasting

deepmind/graphcast 24 Dec 2022

Global medium-range weather forecasting is critical to decision-making across many social and economic domains.

Decision Making Weather Forecasting

3,967
1.22 stars / hour

Generative Representational Instruction Tuning

contextualai/gritlm 15 Feb 2024

Notably, we find that GRIT matches training on only generative or embedding data, thus we can unify both at no performance loss.

Language Modelling Large Language Model +1

186
1.13 stars / hour

Linear Transformers with Learnable Kernel Functions are Better In-Context Models

corl-team/rebased 16 Feb 2024

Advancing the frontier of subquadratic architectures for Language Models (LMs) is crucial in the rapidly evolving field of natural language processing.

In-Context Learning Language Modelling

89
1.03 stars / hour

SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers

willisma/sit 16 Jan 2024

We present Scalable Interpolant Transformers (SiT), a family of generative models built on the backbone of Diffusion Transformers (DiT).

Image Generation

240
1.03 stars / hour

TorchCP: A Library for Conformal Prediction based on PyTorch

ml-stat-sustech/torchcp 20 Feb 2024

TorchCP is a Python toolbox for conformal prediction research on deep learning models.

Conformal Prediction regression

101
0.96 stars / hour

Data Engineering for Scaling Language Models to 128K Context

franxyao/long-context-data-engineering 15 Feb 2024

We demonstrate that continual pretraining of the full model on 1B-5B tokens of such data is an effective and affordable strategy for scaling the context length of language models to 128K.

Continual Pretraining

113
0.76 stars / hour

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

boese0601/magicdance 18 Nov 2023

In this work, we propose MagicPose, a diffusion-based model for 2D human pose and facial expression retargeting.

Video Generation

349
0.74 stars / hour

Extreme Video Compression with Pre-trained Diffusion Models

elesionkyrie/extreme-video-compression-with-prediction-using-pre-trainded-diffusion-models- 14 Feb 2024

The results showcase the potential of exploiting the temporal relations in video data using generative models.

Image Compression Video Compression

85
0.73 stars / hour

Magic-Me: Identity-Specific Video Customized Diffusion

zhen-dong/magic-me 14 Feb 2024

In the field of text-to-image generation (T2I), subject-driven content generation has achieved great progress with the ID in the images controllable.

Video Generation

186
0.70 stars / hour