Pearl: A Production-ready Reinforcement Learning Agent

facebookresearch/pearl 6 Dec 2023

Reinforcement Learning (RL) offers a versatile framework for achieving long-term goals.

reinforcement-learning Reinforcement Learning (RL)

9.10 stars / hour

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

state-spaces/mamba 1 Dec 2023

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.

Language Modelling

8.06 stars / hour

TaskWeaver: A Code-First Agent Framework

microsoft/taskweaver 29 Nov 2023

TaskWeaver provides support for rich data structures, flexible plugin usage, and dynamic plugin selection, and leverages LLM coding capabilities for complex logic.

Natural Language Understanding

6.29 stars / hour

Self-conditioned Image Generation via Generating Representations

LTH14/rcg 6 Dec 2023

During generation, RCG samples from such representation distribution using a representation diffusion model (RDM), and employs a pixel generator to craft image pixels conditioned on the sampled representation.

Conditional Image Generation Unconditional Image Generation

4.68 stars / hour

Magicoder: Source Code Is All You Need

ise-uiuc/magicoder 4 Dec 2023

Magicoder models are trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets to generate high-quality instruction data for code.

Code Generation Text-to-Code Generation

4.62 stars / hour

Style Aligned Image Generation via Shared Attention

google/style-aligned 4 Dec 2023

Large-scale Text-to-Image (T2I) models have rapidly gained prominence across creative fields, generating visually compelling outputs from textual prompts.

Image Generation

3.31 stars / hour

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians

yuelangx/gaussian-head-avatar 5 Dec 2023

Creating high-fidelity 3D head avatars has always been a research hotspot, but there remains a great challenge under lightweight sparse view setups.

2.99 stars / hour

Sequential Modeling Enables Scalable Learning for Large Vision Models

ytongbai/LVM 1 Dec 2023

We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data.

2.89 stars / hour

DemoFusion: Democratising High-Resolution Image Generation With No $$$

PRIS-CV/DemoFusion 24 Nov 2023

High-resolution image generation with Generative Artificial Intelligence (GenAI) has immense potential but, due to the enormous capital investment required for training, it is increasingly centralised to a few large corporations, and hidden behind paywalls.

Image Generation

2.88 stars / hour