SGLang is a fast serving framework for large language models and vision language models.

[Interspeech 2024] LiteFocus is a tool designed to accelerate diffusion-based TTA model, now implemented with the base model AudioLDM2.

A More Fair and Comprehensive Comparison between KAN and MLP

Vico: Compositional Video Generation as Flow Equalization

Reference implementation of Megalodon 7B model

To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.

Explore the Limits of Omni-modal Pretraining at Scale

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 30+ benchmarks

Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"

Code for CVPR 2024 Oral "Neural Lineage"

Accelerating the development of large multimodal models (LMMs) with lmms-eval

A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

FinRobot: An Open-Source AI Agent Platform for Financial Applications using LLMs 🚀 🚀 🚀

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

Receptive field as experts

Official repository of MLLA

[Mamba-Survey-2024] Paper list for State-Space-Model/Mamba and it's Applications

Code for paper "Unsegment Anything by Simulating Deformation" (CVPR 2024)

Experiencing lightning fast (~1s) and accurate drag-based image editing

Multilingual Medicine: Model, Dataset, Benchmark, Code

Adapting LLaMA Decoder to Vision Transformer

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

[CVPR 2024] Code release for TransNeXt model

⚓️ Sailor: Open Language Models for South-East Asia