Compression with Global Guidance: Towards Training-free High-Resolution MLLMs Acceleration

A Telegram bot to recommend arXiv papers

具身智能入门指南 Embodied-AI-Guide

📚 Collection of token reduction for model compression resources.

A paper list of some recent works about Token Compress for Vit and VLM

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Accelerating Diffusion Transformers with Token-wise Feature Caching

This is official library of "ProFD: Prompt-guided Feature Disentangling for Occluded Person Re-Identification"

📚 Collection of awesome generation acceleration resources.

Material for gpu-mode lectures

A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

A generative speech model for daily dialogue.

Example models using DeepSpeed

[ICASSP 2024] VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders

Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following

AcadHomepage: A Modern and Responsive Academic Personal Homepage

ModelScope: bring the notion of Model-as-a-Service to life.

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

my attempt at implementing the DiffEdit paper (WIP)

Speed up Stable Diffusion with this one simple trick!

Let us control diffusion models!

[CVPR 2024] Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning

[ICLR2023] PLOT: Prompt Learning with Optimal Transport for Vision-Language Models

A collection of parameter-efficient transfer learning papers focusing on computer vision and multimodal domains.

Reverse engineered ChatGPT API

Jupyter notebook on Gumbel-max and Gumbel-softmax tricks