MEDITRON-70B: Scaling Medical Pretraining for Large Language Models

epfllm/meditron 27 Nov 2023

Large language models (LLMs) can potentially democratize access to medical knowledge.

 Ranked #1 on Multiple Choice Question Answering (MCQA) on MedMCQA (Dev Set (Acc-%) metric)

Conditional Text Generation Multiple Choice Question Answering (MCQA)

1,037
1.35 stars / hour

StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

GongyeLiu/StyleCrafter 1 Dec 2023

To address these challenges, we introduce StyleCrafter, a generic method that enhances pre-trained T2V models with a style control adapter, enabling video generation in any style by providing a reference image.

Disentanglement Text-to-Video Generation +1

50
1.19 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

439
1.17 stars / hour

SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis

ZiqiaoPeng/SyncTalk 29 Nov 2023

A lifelike talking head requires synchronized coordination of subject identity, lip movements, facial expressions, and head poses.

Talking Face Generation Talking Head Generation

187
0.97 stars / hour

Initializing Models with Larger Ones

oscarxzq/weight-selection 30 Nov 2023

Weight selection offers a new approach to leverage the power of pretrained models in resource-constrained settings, and we hope it can be a useful tool for training small models in the large-model era.

Knowledge Distillation

98
0.93 stars / hour

Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models

yuliang-liu/monkey 11 Nov 2023

Additionally, experiments on 18 datasets further demonstrate that Monkey surpasses existing LMMs in many tasks like Image Captioning and various Visual Question Answering formats.

Image Captioning Question Answering +2

475
0.84 stars / hour

SparseDC: Depth Completion from sparse and non-uniform inputs

whu-usi3dv/sparsedc 30 Nov 2023

The key contributions of SparseDC are two-fold.

Depth Completion

35
0.83 stars / hour

On Bringing Robots Home

notmahi/dobb-e 27 Nov 2023

We use the Stick to collect 13 hours of data in 22 homes of New York City, and train Home Pretrained Representations (HPR).

342
0.78 stars / hour

Qwen Technical Report

QwenLM/Qwen-7B 28 Sep 2023

Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans.

Language Modelling Large Language Model +1

7,097
0.68 stars / hour

Sketch Video Synthesis

yudianzheng/sketchvideo 26 Nov 2023

Understanding semantic intricacies and high-level concepts is essential in image sketch generation, and this challenge becomes even more formidable when applied to the domain of videos.

Video Editing

125
0.67 stars / hour