pixeli99

Pengxiang Li's starred repositories

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

1071700

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Language:PythonMIT92300

ESFT

Expert Specialized Fine-Tuning

Language:PythonMIT9500

Kolors

Kolors Team

Language:PythonApache-2.0250400

FlagScale

FlagScale is a large model toolkit based on open-sourced projects.

Language:PythonNOASSERTION10300

Spatio-Temporal-Shuffle-Guidance

Language:Python300

matmulfreellm

Implementation for MatMul-free LM.

Language:PythonApache-2.0268900

1d-tokenizer

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

Language:Jupyter NotebookApache-2.028000

OpenSTL

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

Language:PythonApache-2.066700

Awesome-World-Model

Collect some World Models for Autonomous Driving papers.

30800

Perturbed-Attention-Guidance

Official implementation of "Perturbed-Attention Guidance"

Language:Jupyter NotebookMIT22400

Efficient-Inference

Language:Python500

know-dont-tell

Language:Python800

cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Language:PythonApache-2.0156100

DriveVLM

Language:HTML3600

LingoQA

Official GitHub repository for the paper "LingoQA: Video Question Answering for Autonomous Driving"

Language:PythonNOASSERTION9200

Underwater-Diffusion

Language:Python100

DeepKE

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

Language:PythonMIT323000

IRASim

Language:PythonApache-2.04600

chameleon

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

Language:PythonNOASSERTION154400

NuInstruct

3900

EVE

EVE: Encoder-Free Vision-Language Models from BAAI

Language:PythonMIT14900

RectifiedFlow

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

Language:Python70100

Open-MAGVIT2

Open-MAGVIT2: Democratizing Autoregressive Visual Generation

Language:PythonApache-2.032500

Pandora

Pandora: Towards General World Model with Natural Language Actions and Video States

Language:Python43500

MimicBrush

Official implementations for paper: Zero-shot Image Editing with Reference Imitation

Language:PythonApache-2.089100

ml-4m

4M: Massively Multimodal Masked Modeling

Language:PythonApache-2.0138500

eye_for_an_eye

Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models

Language:Python1300

MotionClone

Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

Language:Python28300

ctrl-x

Official implementation of "Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance"

7200