Ziyi Wu's starred repositories
clip-as-service
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
segment-anything-2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
AI-Scientist
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
torchtitan
A native PyTorch Library for large model training
Lumina-T2X
Lumina-T2X is a unified framework for Text to Any Modality Generation
diffusion-forcing
code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"
attention_with_linear_biases
Code for the ALiBi method for transformer language models (ICLR 2022)
TransNetV2
TransNet V2: Shot Boundary Detection Neural Network
VisionLLaMA
VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks
unmasked_teacher
[ICCV2023 Oral] Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Netflix-Prime-Auto-Skip
Automatically skip Ads, Intros, Recaps, Credits, etc. on Netflix, Prime video, Disney+ (Hotstar, STAR+), Crunchyroll and HBO max
VidChapters
[NeurIPS 2023 D&B] VidChapters-7M: Video Chapters at Scale
flashattention2-custom-mask
Triton implementation of FlashAttention2 that adds Custom Masks.
VideoScore
official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]